tardis-27b-ternfull-k1 / compact-progress.json
CodeMasterCody3D's picture
Upload compact-progress.json with huggingface_hub
301f4a2 verified
Raw History Blame Contribute Delete
470 kB
{
"complete": true,
"completed_shards": [
{
"file": "compact-00001-of-00002.safetensors",
"sha256": "4019d870a320c54b48f0e729b9045f5cf65e76bf38386253aaa03e3a3f22554a",
"source": "model-00001-of-00002.safetensors",
"tensors": 783
},
{
"file": "compact-00002-of-00002.safetensors",
"sha256": "8a4360885b4bf9c002d879461e22f8562d2ec05ac5df1afb449884abdcaf9251",
"source": "model-00002-of-00002.safetensors",
"tensors": 67
}
],
"copied": [
"tokenizer.json",
"tokenizer_config.json",
"chat_template.jinja"
],
"entries": {
"lm_head.weight": {
"file": "compact-head.safetensors",
"payload": {
"packed": "t_7866b85ef9fdbeac35f2f699fd08c8b431545344f6f1cd1600c342dcec2a3a6e.packed",
"scales": "t_7866b85ef9fdbeac35f2f699fd08c8b431545344f6f1cd1600c342dcec2a3a6e.scales"
},
"spec": {
"dtype": "float32",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "float32",
"shape": [
248320,
5120
],
"version": 1
}
},
"model.embed_tokens.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fcd443ac9b03e52a95700c47160a158afd6efde971065f92a4a1dec5532d0b84.packed",
"scales": "t_fcd443ac9b03e52a95700c47160a158afd6efde971065f92a4a1dec5532d0b84.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
248320,
5120
],
"version": 1
}
},
"model.layers.0.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_82d8e74f397e5262dc66ad898551a031234f3f950348f40e6fe9f22766d890af.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.0.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_eadf4b2f99e6d9370906b9bb7271f049ac59391a37196bfa274e336609e3ce20.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.0.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_84f3f44b4a30623701abcfaa588e0d717f7e0ecea4f61d7a645b6671b2f00fd3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.0.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ca226c8c81dbea71e1d15485c8c93d07dcec1fbf83fad35d70534b25538092d3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.0.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a130db7517e8bb1e0b08801e2bd2dbe4fa12a984b5f8ba319aae58d7e13e4da0.packed",
"scales": "t_a130db7517e8bb1e0b08801e2bd2dbe4fa12a984b5f8ba319aae58d7e13e4da0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.0.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_181bbcb80e628b665462ecbd29aa0f580523efa97a781d36012da4ace3896954.packed",
"scales": "t_181bbcb80e628b665462ecbd29aa0f580523efa97a781d36012da4ace3896954.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.0.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_dd65ca2ad3f650d42eafa5fcb3d7d8f2fc34e61dc676eb64d0b7b1a18828730c.packed",
"scales": "t_dd65ca2ad3f650d42eafa5fcb3d7d8f2fc34e61dc676eb64d0b7b1a18828730c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.0.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_eeb823bf05002d838abb01e7d4bdaddb9a57c2c4cb938d9ac3c2035662ab44fb.packed",
"scales": "t_eeb823bf05002d838abb01e7d4bdaddb9a57c2c4cb938d9ac3c2035662ab44fb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.0.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_de7ced0590c2f2bda1e99b0d77b0818d1151d2f482b0c65dcbf24e6b334f75b4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.0.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0a0ec15eac324423ec6c96e85608dfbcff86dac7fada16c82212749a7d46299d.packed",
"scales": "t_0a0ec15eac324423ec6c96e85608dfbcff86dac7fada16c82212749a7d46299d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.0.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d2a1882a121cf2556c84e17b6c20f0234ee80b1cf85d83d98dcfc65d25142a22.packed",
"scales": "t_d2a1882a121cf2556c84e17b6c20f0234ee80b1cf85d83d98dcfc65d25142a22.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.0.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8be6ea8bb62dfe12e57646009396a053198cd148c720c14dbd017008391736bd.packed",
"scales": "t_8be6ea8bb62dfe12e57646009396a053198cd148c720c14dbd017008391736bd.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.0.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_af2865b166081381b66e1277bb7064111f7e3ec3ae54694e1eff44dc17a472f6.packed",
"scales": "t_af2865b166081381b66e1277bb7064111f7e3ec3ae54694e1eff44dc17a472f6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.0.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0786790687f6be07f618ad56f3f5b89b84f6eab0076f9ed8adc27e71dabbb653.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.1.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_645cb79f790a40261a07d2ff771e3278f99342bd52399c701741a6fa80425201.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.1.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ee97e34d0d8ebf91c610a862380992e47021e91f0310c33fb962b94a89625377.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.1.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5b1e8d4517b882212f55c905d289999dec63852f13bf4d97fae257ea6677c563.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.1.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ce41f103eb599cf17e131d7a578c06e3b6e026e8fee645beb320a8be744146f8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.1.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_df56026ec0c1237bb28c2dc26634222d14da8a7b86a52e0eacd6c100168553a8.packed",
"scales": "t_df56026ec0c1237bb28c2dc26634222d14da8a7b86a52e0eacd6c100168553a8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.1.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cc3ac8918d430316c82491e12539a382309889d45f60fc0190cf5b72b7ab01e2.packed",
"scales": "t_cc3ac8918d430316c82491e12539a382309889d45f60fc0190cf5b72b7ab01e2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.1.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a698f0f723364aa64c8e35c82dcbb9c8b6194f9aae14d849b93ddfd7220d7388.packed",
"scales": "t_a698f0f723364aa64c8e35c82dcbb9c8b6194f9aae14d849b93ddfd7220d7388.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.1.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1dcbca15506dfb171a2a6fc78333120b6763731c68fe89dbd8f4be0d5498127b.packed",
"scales": "t_1dcbca15506dfb171a2a6fc78333120b6763731c68fe89dbd8f4be0d5498127b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.1.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_46e54a10e28f37ece93608dad50350ebac68c71cc130c859e92204152e27881f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.1.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_68c194668c87067728a681542c0ae03c6c4bf12a001168cb2d0a7663686f1e37.packed",
"scales": "t_68c194668c87067728a681542c0ae03c6c4bf12a001168cb2d0a7663686f1e37.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.1.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_65c627d24d2e2d4232f1d949f818330c52bdef9879beb5a120a17410552d0ee0.packed",
"scales": "t_65c627d24d2e2d4232f1d949f818330c52bdef9879beb5a120a17410552d0ee0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.1.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c2c3057b477cf2fdf93d03fbd29398a1c9ceb6a7828c5b1df9479f87952b2e99.packed",
"scales": "t_c2c3057b477cf2fdf93d03fbd29398a1c9ceb6a7828c5b1df9479f87952b2e99.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.1.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_747a8f048ab61af37e26d4ad198827c408e343cdf3bdfb78475251429a34a1f4.packed",
"scales": "t_747a8f048ab61af37e26d4ad198827c408e343cdf3bdfb78475251429a34a1f4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.1.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_63c24c911e06102c953e1e2c04302692d9473c0b96c094becc3bec78442c12ca.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.10.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4eefbf0ad27bcfcc9a298eb603f24b6543b453a263298a6fb7bc3c9e35e242e5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.10.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e5f75d878af9cd022920ee80faec53dd97134cf975dcb2a88f9aef64ee58165c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.10.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5f924a682aa5764575693f9a1dafe9ec10aecf624059ec22b473c5f1f44268b7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.10.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7280fdc1a869291c623fb7080a711fd8c35fba0d39fc763c33dbb91b1d6069c1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.10.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ce2378813369b169016e41fbebd8b1819aba96376e5b2495baed610c485b8a60.packed",
"scales": "t_ce2378813369b169016e41fbebd8b1819aba96376e5b2495baed610c485b8a60.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.10.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e962f3e51b7d0c76266531f0cf68529813aec77ddc5845b8dde6bae97bce17fa.packed",
"scales": "t_e962f3e51b7d0c76266531f0cf68529813aec77ddc5845b8dde6bae97bce17fa.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.10.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7444ba4559b13413e84120a74e1ee04a7c7995c153198b6fa945fa6fc205e17a.packed",
"scales": "t_7444ba4559b13413e84120a74e1ee04a7c7995c153198b6fa945fa6fc205e17a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.10.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b464f1c7043ae5261ff4b9f68632916c5c2ca8239faef2cad9203fd748d7e050.packed",
"scales": "t_b464f1c7043ae5261ff4b9f68632916c5c2ca8239faef2cad9203fd748d7e050.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.10.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_dbc0c9f6a9a0da342d326835b9ed62e19d3648314f3c6371c821e97bb3be2e30.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.10.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_37d8dca4db6bece7778238a4cbb9c5531be6f12d7d7cc2984e2d859a50ca0953.packed",
"scales": "t_37d8dca4db6bece7778238a4cbb9c5531be6f12d7d7cc2984e2d859a50ca0953.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.10.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_301d3c8eada4ca020cded17bd5c623d9dd7fd56880e1425a18f87701994107eb.packed",
"scales": "t_301d3c8eada4ca020cded17bd5c623d9dd7fd56880e1425a18f87701994107eb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.10.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_37649d676c77828ac99bdce08c8f883ef06470db6a1fb38a0d27260f0c12aa22.packed",
"scales": "t_37649d676c77828ac99bdce08c8f883ef06470db6a1fb38a0d27260f0c12aa22.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.10.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_41ce24a2be18f66d6ddefe1fbf380845e899db7f505852ea7a59122920eef2bb.packed",
"scales": "t_41ce24a2be18f66d6ddefe1fbf380845e899db7f505852ea7a59122920eef2bb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.10.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_fefb95f52fa2c374e5bd4a6af97e341619daa192bff3dc64beb2e05dbd220698.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.11.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_809105658299a47cae7713d2c146178edd45298947ed68ef9e14b579fa59cb1c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.11.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ee911ca1953306406479d8d64006f5a393ee9c0d5598ffba83345e334e9f4f2d.packed",
"scales": "t_ee911ca1953306406479d8d64006f5a393ee9c0d5598ffba83345e334e9f4f2d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.11.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b2cdbb1d0883dee4ba89c9198e5cacedf4c02cb3a0e3578a1b2b3d98f6b986df.packed",
"scales": "t_b2cdbb1d0883dee4ba89c9198e5cacedf4c02cb3a0e3578a1b2b3d98f6b986df.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.11.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_deee12cef2ec094c095791577b95206eebff50f614533203c11986ec191d1b06.packed",
"scales": "t_deee12cef2ec094c095791577b95206eebff50f614533203c11986ec191d1b06.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.11.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ffad962cf8fedc589107c9a806bcebc77f5ce5bf9705fb7afe34ff6dcaddd6ce.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.11.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b9152d571c01123069c5790336a1f98249eebc1964c37db3bd11dff719fb7037.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.11.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_92372c372b1af91759355448a0a0348d4e7a53cd7b1114651118a3a94d268447.packed",
"scales": "t_92372c372b1af91759355448a0a0348d4e7a53cd7b1114651118a3a94d268447.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.11.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b78f2e901585a120aa186e0163c92e59d82c364565ff1c120bcd1db9d206ae9e.packed",
"scales": "t_b78f2e901585a120aa186e0163c92e59d82c364565ff1c120bcd1db9d206ae9e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.11.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4187013ab8c8c545f4a8ee61485c11b9f0f3bc2d9a7dd525b94d947a7901a0ae.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.11.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0f8a68fd8b8e38bd2c0485fc1b8bfbb82db8aaf70f2aa946ff714aedfd60673e.packed",
"scales": "t_0f8a68fd8b8e38bd2c0485fc1b8bfbb82db8aaf70f2aa946ff714aedfd60673e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.11.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8f46f27101111611bc88f3bd1f7cca5a9c789e2f94f4e4e9284bdc14dd586ecd.packed",
"scales": "t_8f46f27101111611bc88f3bd1f7cca5a9c789e2f94f4e4e9284bdc14dd586ecd.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.12.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1f13f4de7005c677bb7173dba9cde4b698a2354dc7e4b7f108ec265e9e0a2685.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.12.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d2fd95c295608b48492dab4faf24e145147905c0dd52cf791a58802516c440e3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.12.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1eab034c2ac54f435e91d9d024ce40c60462006770bb8b22a5e6568c07b541eb.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.12.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_da27363bbf9585bb4e5d51869114c1fe9ef2d9441b68e980a3f00b761acb9d22.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.12.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9e53c58c2426f2fdb0f02c91b2088ad8b2168bfbd12e2e3e0c871291c2a709a7.packed",
"scales": "t_9e53c58c2426f2fdb0f02c91b2088ad8b2168bfbd12e2e3e0c871291c2a709a7.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.12.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d16b822f34fd2b87de2ed313abbf11e1a532f3df3a43100c96057b03df1c805b.packed",
"scales": "t_d16b822f34fd2b87de2ed313abbf11e1a532f3df3a43100c96057b03df1c805b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.12.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cec5d5878c31c4a637fd8bdf195501adb26c4e80f0c7966c3f69cd9400986fd2.packed",
"scales": "t_cec5d5878c31c4a637fd8bdf195501adb26c4e80f0c7966c3f69cd9400986fd2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.12.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2ca446e1a3de96a0d6b728171b747a8061aa2600182a015c4c319e33b1c8245d.packed",
"scales": "t_2ca446e1a3de96a0d6b728171b747a8061aa2600182a015c4c319e33b1c8245d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.12.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ae9eeaaf3c3e486b2d2485cd30277e2a077442b9b7b9a9bf83d99b1bb1149db4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.12.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cc0fdc839e51cbede317f62cfdc64478d789e888f8706689507edd42913563cc.packed",
"scales": "t_cc0fdc839e51cbede317f62cfdc64478d789e888f8706689507edd42913563cc.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.12.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_74f265a2c83670774183b8eb93c78d29f76984660efd40ada3928a97ca93967c.packed",
"scales": "t_74f265a2c83670774183b8eb93c78d29f76984660efd40ada3928a97ca93967c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.12.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b9f7fc4a92512ce89d1fe7c30e668d18f817074f04ea1ba1bda10ecdc66e8520.packed",
"scales": "t_b9f7fc4a92512ce89d1fe7c30e668d18f817074f04ea1ba1bda10ecdc66e8520.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.12.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_58634067806beb74f975f275c360d78400b60b2c295bd9253bc3faee44e8122b.packed",
"scales": "t_58634067806beb74f975f275c360d78400b60b2c295bd9253bc3faee44e8122b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.12.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a8444632f18a0294434c4e57f5999a0886ae33b96bb63b2d1e42e1f9df771893.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.13.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_65286713fe800953bc63d5ceaa84987f10a4d832b438b88904b8871719c4098a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.13.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1c930528797a28abe67fac644aeede0584b11bad2eb37b3de800fad7e98c6d8a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.13.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_905d5d77bf3d471deebdfa60863dc52712b84f4665d8bac0044afbd333ddf0f1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.13.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_491b54118201f8a755494ded298b7fec1c49f91ffb003bdb1c3ace82dd18a49e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.13.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7b9f5e092b8745c7b53356a4228e58a44e53dce2f28052239ddb69aa61b6c29d.packed",
"scales": "t_7b9f5e092b8745c7b53356a4228e58a44e53dce2f28052239ddb69aa61b6c29d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.13.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ad6b7c1225d6d5e7b2d0f5195d6c0d45638d630305b061db7697f25e2e0341fb.packed",
"scales": "t_ad6b7c1225d6d5e7b2d0f5195d6c0d45638d630305b061db7697f25e2e0341fb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.13.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_100372850bf966814f626fa69b249812e769f6483486c232eaee54d3f7adc134.packed",
"scales": "t_100372850bf966814f626fa69b249812e769f6483486c232eaee54d3f7adc134.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.13.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_215bdc1d2f5878d169692154c0ca540572a6d392b2436e754f113916638db788.packed",
"scales": "t_215bdc1d2f5878d169692154c0ca540572a6d392b2436e754f113916638db788.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.13.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_92da316eb71965f5488a26ed6e85d0b838bd1ae09def89743a8e387670514e41.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.13.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_be42490741b14b748a2bde6563b3e1bdd9aab383794e16fc32e19f6b93c1d304.packed",
"scales": "t_be42490741b14b748a2bde6563b3e1bdd9aab383794e16fc32e19f6b93c1d304.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.13.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d218a1914274b614838ca8b30d1c52f81ffa670edd7a839719730b44b308bc74.packed",
"scales": "t_d218a1914274b614838ca8b30d1c52f81ffa670edd7a839719730b44b308bc74.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.13.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_919f12ad88fcde0deb757829dd1abb8b128fe1fba45e2157cdf6ae917bf723e2.packed",
"scales": "t_919f12ad88fcde0deb757829dd1abb8b128fe1fba45e2157cdf6ae917bf723e2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.13.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_023633e29f7c802b822517e532846b9c8a95ecead2aa295203047624e92db3b2.packed",
"scales": "t_023633e29f7c802b822517e532846b9c8a95ecead2aa295203047624e92db3b2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.13.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_be31caf579e327aee8af491eab780e84eb96117f937260434c4a2f4ecc1a334e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.14.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_eea4fa8955685e04f3b3f6c1ad54d6533c47c3495cbf75f62ea80954e12493d9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.14.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e0780c31301fe1cb8bfacdb93222b6be096895c2f4a0ceffe494f33de28e164c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.14.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_687e0f6ed8f76e44d5d4a75aaf8c4b530bae13edca70c284b980d3bad791f7c9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.14.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d4a0ca75a04f8d06fbee8677c7c2567e2b520c0cb1f4ee8a3a16a1646ed23af8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.14.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_505ebc2c70f2bd06b1ae46c66d146fea38da2c2d0964f0b59f3bb3fb4fcf3a96.packed",
"scales": "t_505ebc2c70f2bd06b1ae46c66d146fea38da2c2d0964f0b59f3bb3fb4fcf3a96.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.14.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b6ba2b2e84054bd06a5f0b78f5e7754218f23531d84084c05f696352a3905dbb.packed",
"scales": "t_b6ba2b2e84054bd06a5f0b78f5e7754218f23531d84084c05f696352a3905dbb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.14.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_083fcab460bcc68627984734a85400ed093f9e648d91e747f3cc5c5d4a1145b9.packed",
"scales": "t_083fcab460bcc68627984734a85400ed093f9e648d91e747f3cc5c5d4a1145b9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.14.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_627e4a611aba96bdf170e9ed901f5a2212531e87b65c50db61c7f915e371b115.packed",
"scales": "t_627e4a611aba96bdf170e9ed901f5a2212531e87b65c50db61c7f915e371b115.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.14.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8954c782c2c7eb163b6a195157911131d08db80f2cce1430df7e83c533a86467.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.14.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_29720bc06af6dab91c3b57614db6bc087f756b459c5fc42fef8c784d75f2125b.packed",
"scales": "t_29720bc06af6dab91c3b57614db6bc087f756b459c5fc42fef8c784d75f2125b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.14.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7e094f3964cfc90f9ef8efafa297f7159c663d0b5f5cfac6f2b803d91a340a7c.packed",
"scales": "t_7e094f3964cfc90f9ef8efafa297f7159c663d0b5f5cfac6f2b803d91a340a7c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.14.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d86480fa19797ad1ff1ff2a5d831b2d562a8c11716cbe2b8a373016e907fea7d.packed",
"scales": "t_d86480fa19797ad1ff1ff2a5d831b2d562a8c11716cbe2b8a373016e907fea7d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.14.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_320d360207b765505b6eb46a8b16441cdf3743e4d1efb5d6d7236f6f69fb5bb0.packed",
"scales": "t_320d360207b765505b6eb46a8b16441cdf3743e4d1efb5d6d7236f6f69fb5bb0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.14.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_93718ec0ee84316fe4b19fa727fbce33893dc9d504efbd5fc983b2bf1ca93dd2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.15.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b67a332d6a3b914816fcf7d5bf7fc9de1b611eca69afd455eb5567970ca6389a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.15.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c217985ee66b5975228ab2ec5318a52f363c425cf964b682622da7380a8effe3.packed",
"scales": "t_c217985ee66b5975228ab2ec5318a52f363c425cf964b682622da7380a8effe3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.15.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_730fd37738341e3f59a38bbba79aa80e3c5b0e135a229bc89ac2d1d54170debe.packed",
"scales": "t_730fd37738341e3f59a38bbba79aa80e3c5b0e135a229bc89ac2d1d54170debe.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.15.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_189541baf9599e9e0d6300bb46d764a3d5d5ab4f60a2bad11c151c658ad99b3c.packed",
"scales": "t_189541baf9599e9e0d6300bb46d764a3d5d5ab4f60a2bad11c151c658ad99b3c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.15.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f8afbeed531ca1693f5700256be2fee78b82a1a0a1b0e2024af5f80dee1a5489.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.15.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6248266306eac89a002a3ab878951f4f26624606232a5023d54b78bd5a2b3ef3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.15.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fd24fff8e117e8fe75597938b3d8f30f23076f5c357c81c4e6fe542100e07eaa.packed",
"scales": "t_fd24fff8e117e8fe75597938b3d8f30f23076f5c357c81c4e6fe542100e07eaa.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.15.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_04d0a22ccb34a0a030918b5591ba35746ce1a07a45d71a3e8e047145b9b6a468.packed",
"scales": "t_04d0a22ccb34a0a030918b5591ba35746ce1a07a45d71a3e8e047145b9b6a468.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.15.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_651db91ca0eec4e56e4fe9b650679381d7bfcb5937911232c0813ab44589f759.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.15.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8aad4c42ad566266dc0a232145894de2320bc6c32f19faa1b4da381edd78cc60.packed",
"scales": "t_8aad4c42ad566266dc0a232145894de2320bc6c32f19faa1b4da381edd78cc60.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.15.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f566ee0ee912ad62ffc49e7d0af4991007e0974cb9dd657e51138e0a36c86284.packed",
"scales": "t_f566ee0ee912ad62ffc49e7d0af4991007e0974cb9dd657e51138e0a36c86284.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.16.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_da2854a5da76e4e611bdd989466d1ffc8f603583e7ad21c476d27e41e103e1e9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.16.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0e865ea70495f1df79737938d33e72b8594679e9b0cb3d7a1146689cc2705064.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.16.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_fd43e77520bbb2540365b64d3178bb02f486abf86410c3b1b94d165de36e928e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.16.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3bc088259214a619ad6b5e4a48989b3d2a6ebcaecd3d4a4f6950717d1f2807ec.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.16.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1574d7202ed04843b01296526d8618ab18224031b7610cb5f4efdb93b868db72.packed",
"scales": "t_1574d7202ed04843b01296526d8618ab18224031b7610cb5f4efdb93b868db72.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.16.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fc3f850e6629fec15c46bbed7602a2dd48a40a5ac798e46c21de4440a2fd0073.packed",
"scales": "t_fc3f850e6629fec15c46bbed7602a2dd48a40a5ac798e46c21de4440a2fd0073.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.16.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b80b884a85b2642da34585e21983ca191cc7fd2203f2c604d47970b23d3131df.packed",
"scales": "t_b80b884a85b2642da34585e21983ca191cc7fd2203f2c604d47970b23d3131df.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.16.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f2baa43eb253052b3a398f0435a583a0994e9b9194692bce9099188e2f420808.packed",
"scales": "t_f2baa43eb253052b3a398f0435a583a0994e9b9194692bce9099188e2f420808.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.16.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_2b5fb2444460f45f9d809e758a2bbab64d9747ef8ead1ac9a13ed7a3dcc97c6f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.16.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b951c51884bb014373aab6baf4389ef94a7fd97e529e7de10fba0584688a0c0a.packed",
"scales": "t_b951c51884bb014373aab6baf4389ef94a7fd97e529e7de10fba0584688a0c0a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.16.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8e226eed27106180533124b2a5b8a790c25a7e59c922d0ef501bdcd4e98b6434.packed",
"scales": "t_8e226eed27106180533124b2a5b8a790c25a7e59c922d0ef501bdcd4e98b6434.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.16.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ecacbca74030168c8fa0c15f3f29d2114f69fdbbce1fe035bba8084439a0bb96.packed",
"scales": "t_ecacbca74030168c8fa0c15f3f29d2114f69fdbbce1fe035bba8084439a0bb96.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.16.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a92733774c581fe236e2bf5b74041299980c1f7875836447af5f3265a51aac98.packed",
"scales": "t_a92733774c581fe236e2bf5b74041299980c1f7875836447af5f3265a51aac98.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.16.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6c6a8d7c11c886d2c3a87dfd67ce6fcb9889e7f4d8d1ac2adfe8d69c1f3443f5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.17.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9acb40949d03d03556fb37f768e2d707fe4a06070865d5eec8d4c57ca7356361.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.17.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_643f0a68a778b64c3468d56c867e06db4f85af05f54b2eb976022c9d219978a9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.17.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4b3bfc26cf3b39e3a19ca2eac4b96133fd643e6c7829c1faeb194719fa6a1654.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.17.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_aecf011b8617fdc9db68cc9e2636e08a7e45113ef8b7de0fa4a112da768bc48f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.17.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a0bc405c10658f1760093cc4d9d9629f6038418e1154c5b16d3a98648aeec2ef.packed",
"scales": "t_a0bc405c10658f1760093cc4d9d9629f6038418e1154c5b16d3a98648aeec2ef.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.17.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6b642ad630960f1dc56317608e32a226ba5fe549341f720ad25f50b6070f974e.packed",
"scales": "t_6b642ad630960f1dc56317608e32a226ba5fe549341f720ad25f50b6070f974e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.17.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2a731a1b8e4cdc59d41e961c865a60074869ae0789664b6f70211954382b48c1.packed",
"scales": "t_2a731a1b8e4cdc59d41e961c865a60074869ae0789664b6f70211954382b48c1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.17.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_93df02b8928b28372ee0f7130c439f0f6d432a0d79bb4c712dbc11b553deae62.packed",
"scales": "t_93df02b8928b28372ee0f7130c439f0f6d432a0d79bb4c712dbc11b553deae62.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.17.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a1ab58a584f2b4a8199cc61ef07d313a1d179f7e0a6632d17ad5cdfa5dda22ad.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.17.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6e719ab0f4b67d92fa405f92b8c8c0d71bed86870017103819f797560223837b.packed",
"scales": "t_6e719ab0f4b67d92fa405f92b8c8c0d71bed86870017103819f797560223837b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.17.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0c8bc9f749e9d418d5af25ec6e8b9ace764aef8ca2fdf263443a8ff35e943471.packed",
"scales": "t_0c8bc9f749e9d418d5af25ec6e8b9ace764aef8ca2fdf263443a8ff35e943471.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.17.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d32bd779f48b8eb1adf267bfadbde472dc651139618b6e87749af516c411afc6.packed",
"scales": "t_d32bd779f48b8eb1adf267bfadbde472dc651139618b6e87749af516c411afc6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.17.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_36ddda719ee99d00f447284db316c3be7127f60f5e3849db246f17e60a0d1658.packed",
"scales": "t_36ddda719ee99d00f447284db316c3be7127f60f5e3849db246f17e60a0d1658.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.17.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0725e1413f7161b6f053393842608814ee7302b9479564516ea7d5c22bd2d552.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.18.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c48c6285df7ec992513590da276dcb6738af8e129dc6b3bf0b9175c1b50f692e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.18.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_81c07acc347df65a7a00ed7437ade8a5564f99dd174605bcbe14cf1bf7581172.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.18.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c601aec76529c97701f88f2841eaa90ae8982ea315e808d837d3bda3904903bc.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.18.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6fef005f524753a9e3b77ac8a5bc4051d9d329aba27f33dfe8a9a319c9770366.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.18.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_475fa4e0a1ef07d22c9de412e0150a57668be28ae471b94f7470480d1d1ba58c.packed",
"scales": "t_475fa4e0a1ef07d22c9de412e0150a57668be28ae471b94f7470480d1d1ba58c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.18.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_87326c2e02654e8fd18b8eb13686ee73f1da17ad1c2c0e5d60c1be10d9c805db.packed",
"scales": "t_87326c2e02654e8fd18b8eb13686ee73f1da17ad1c2c0e5d60c1be10d9c805db.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.18.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ed0a74f6e0107261985b49e479edcb836270b8c2df36691a4ea444358e6a6f25.packed",
"scales": "t_ed0a74f6e0107261985b49e479edcb836270b8c2df36691a4ea444358e6a6f25.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.18.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b9fc7a70f3163e1a0e525d403840442bc398ef152a284c99c66f68a88c752e46.packed",
"scales": "t_b9fc7a70f3163e1a0e525d403840442bc398ef152a284c99c66f68a88c752e46.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.18.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5f71a5519102000477bcfb5636409f65079a77ca8ba9e664e8f2137361958369.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.18.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_41f6a8e1123b124924ad94a6bab39cf343a0a9c128caf17702515b0dbcb6eff3.packed",
"scales": "t_41f6a8e1123b124924ad94a6bab39cf343a0a9c128caf17702515b0dbcb6eff3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.18.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_98a11b90eb4743c61364d1c36a77f9bcf5ccef5d774a4c6ac2667410339dc035.packed",
"scales": "t_98a11b90eb4743c61364d1c36a77f9bcf5ccef5d774a4c6ac2667410339dc035.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.18.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_090e6f4eb0236d72074af172589ed9d0f6058aeac40641d6dc180ae82c58cbfb.packed",
"scales": "t_090e6f4eb0236d72074af172589ed9d0f6058aeac40641d6dc180ae82c58cbfb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.18.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1afbf2560c818bc958f37c0a78b2756da55eae68d2ea5b4628cdc9311ad394f0.packed",
"scales": "t_1afbf2560c818bc958f37c0a78b2756da55eae68d2ea5b4628cdc9311ad394f0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.18.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_38428dbf10bb53937d5ae614af4043cd0ef449c4d3a25d5ac68dd686cafa96e7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.19.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_80cac66cb1884eb19ac2a225a73e966f31eb2d5237ccce7a11601f6aa17b0b68.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.19.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_68db2699b33f1ebfb40b46e92c96089a65c3c96a77227a8db3f4b661e6b9e7c5.packed",
"scales": "t_68db2699b33f1ebfb40b46e92c96089a65c3c96a77227a8db3f4b661e6b9e7c5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.19.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7e3cd977e6ee8ea77692d782f28d8ba3b519e1fdde3dceeac64a51d2a66567f8.packed",
"scales": "t_7e3cd977e6ee8ea77692d782f28d8ba3b519e1fdde3dceeac64a51d2a66567f8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.19.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cb98bdacc3488af7589e765c2c0b57e15881d3fa9d55ba6f483caf0ae6daa265.packed",
"scales": "t_cb98bdacc3488af7589e765c2c0b57e15881d3fa9d55ba6f483caf0ae6daa265.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.19.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_52c7d168e94da025e086d2a7cf14294434cb3f7614b04636238b212c34bbcfb0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.19.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6229f707bed4f6fddd8d641f44941db188267be2b8420dafcbe5193130c9a726.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.19.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_15e54ae88f99e146e2d12e75cbe24880c00077c27652cf07273a170aed71c562.packed",
"scales": "t_15e54ae88f99e146e2d12e75cbe24880c00077c27652cf07273a170aed71c562.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.19.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6bf0e3538c9834b26b8282f28e6d16c3a6eaa78d95c0f514e0ad02e04be3c5eb.packed",
"scales": "t_6bf0e3538c9834b26b8282f28e6d16c3a6eaa78d95c0f514e0ad02e04be3c5eb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.19.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6edb1aec5c19362dad1cbfba68ef4869c5c5a9faca8af187f36fd520e384cddb.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.19.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_63e71490454780aa1af5748fb1bb94a6e245c519d7878ae9ae5a23173eb4c9de.packed",
"scales": "t_63e71490454780aa1af5748fb1bb94a6e245c519d7878ae9ae5a23173eb4c9de.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.19.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4805c13b563430419b34e92746b5d1a89acfdde56dfe3bf88541f80128581cc2.packed",
"scales": "t_4805c13b563430419b34e92746b5d1a89acfdde56dfe3bf88541f80128581cc2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.2.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8b017c28cb9eb31f05546d7c80afc94f174bb79b077896abb2b9a8604da8b820.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.2.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b8112da4e9838405543a3f6ddceec3617b76863473c276fcfc67b0b1022c254e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.2.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_daf9bd9c85630d047fb811086b3ae4bcd1b1732825f35f59b324ea0952a9af48.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.2.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7c032a8e505b758cbd33e6b4caa2d84c520b5fba1263eb6d302d9f5038ef10cd.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.2.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_dc90a2da85ce7ded77800d98d77677cdd43e56097aed5afb68d96e893b529213.packed",
"scales": "t_dc90a2da85ce7ded77800d98d77677cdd43e56097aed5afb68d96e893b529213.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.2.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e36e9a8c4ae57569264d146eb23cd16f35b012cfe5e557e9c5120a021e1e00a5.packed",
"scales": "t_e36e9a8c4ae57569264d146eb23cd16f35b012cfe5e557e9c5120a021e1e00a5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.2.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4558c4079b122c2b88f4802a0f8f524fd6f867b1a6769c102910ba290d3c43f1.packed",
"scales": "t_4558c4079b122c2b88f4802a0f8f524fd6f867b1a6769c102910ba290d3c43f1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.2.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cec4fc625dad9c273715196c822bf88bfa93246429d776ed7ee97e66e77a6d4f.packed",
"scales": "t_cec4fc625dad9c273715196c822bf88bfa93246429d776ed7ee97e66e77a6d4f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.2.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_35b347315fe27490e0d850eedb842844c5b05c65f068a2c9b39bb95c20514f8a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.2.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_936810f6883d13366bfb99ec4b2e1928d1bc4f7951dd37b4c10eb9bdc526a664.packed",
"scales": "t_936810f6883d13366bfb99ec4b2e1928d1bc4f7951dd37b4c10eb9bdc526a664.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.2.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a4287839753c83f23c0b1ed5de0a1022a21d2c5ea439d4d86b7b2e930254c0d2.packed",
"scales": "t_a4287839753c83f23c0b1ed5de0a1022a21d2c5ea439d4d86b7b2e930254c0d2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.2.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9a6815ac9cd8cc80a3cbf535a54ca4d26381969387982e3cf6e3eee009dcd6af.packed",
"scales": "t_9a6815ac9cd8cc80a3cbf535a54ca4d26381969387982e3cf6e3eee009dcd6af.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.2.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_777ceb68b74b0323c4a223fd1dcd789fa03838b41f6345125b74de0a326e24d3.packed",
"scales": "t_777ceb68b74b0323c4a223fd1dcd789fa03838b41f6345125b74de0a326e24d3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.2.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_275adb5129f928006a23364e2975fd94c93bab1fe615145379f22c7fe9c9b0ae.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.20.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7b4d71c452e731f8587bcb6175a6e13ba992124b6989eddc3fd64350a7d9706f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.20.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_34a182fc4067d462cba00c8c0fea7aaf7bd92804473a3737e6f61a730b2069da.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.20.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6a451eb09eeb5509bdef488a57670b6fb803e4930c7ca8c88c7a18040bdf9736.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.20.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_15678cbf32a03f8bc6ab8bda338cc7057f901a56ce3131f1724e1ef8ff95c896.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.20.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_be5ce39e471bf694e05759a24aada4a76d3e11adcbb21f660973cdea384c63b8.packed",
"scales": "t_be5ce39e471bf694e05759a24aada4a76d3e11adcbb21f660973cdea384c63b8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.20.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c0eaa1ad211f68f3ccf2e5d4336289b4b041c76077d7ff40dae3fa8ff8fbe88c.packed",
"scales": "t_c0eaa1ad211f68f3ccf2e5d4336289b4b041c76077d7ff40dae3fa8ff8fbe88c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.20.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a6ee82a0778ec1520fceffcc668031df0678d5cf10843793050ecc46afeda7c4.packed",
"scales": "t_a6ee82a0778ec1520fceffcc668031df0678d5cf10843793050ecc46afeda7c4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.20.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7c6ec3696e5edaaf9d9156c29485b755b01b5b23dd6864ba78d6cdb3fc6d048a.packed",
"scales": "t_7c6ec3696e5edaaf9d9156c29485b755b01b5b23dd6864ba78d6cdb3fc6d048a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.20.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_005cbac600e7be9b8cf3fe97e0718dc72bb37afbf2c7d63c6cc045f115f6be9d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.20.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_124b88b82b2e8bcdf18034791440bc21df5c85b645cd476cd9ff58c341595d97.packed",
"scales": "t_124b88b82b2e8bcdf18034791440bc21df5c85b645cd476cd9ff58c341595d97.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.20.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3f107f674c48b81d0d3fbcc9375a4b92ab766719916a3f520061fcbef6c1d7ca.packed",
"scales": "t_3f107f674c48b81d0d3fbcc9375a4b92ab766719916a3f520061fcbef6c1d7ca.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.20.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e34ddbd0a936f7605ad48a9d1ed3115f77021b203ddb6f05a7e90b7890b74dc7.packed",
"scales": "t_e34ddbd0a936f7605ad48a9d1ed3115f77021b203ddb6f05a7e90b7890b74dc7.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.20.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a2c91cf0c7e232870816bf1e254c3da9ae3fcaded4e497b02e425926c667ce67.packed",
"scales": "t_a2c91cf0c7e232870816bf1e254c3da9ae3fcaded4e497b02e425926c667ce67.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.20.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ae803bf28060715aaf05439cfac050b159d0c81ae4c99155785ef28e5af0e8a2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.21.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8058a464fedd78554e4bdbd67af8883c4834b437641a15a66975fb45d8f9c2b9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.21.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5f2d3a8aade01d7ef0c487e74b7febd7b5bf28ebcf26e34aeb845c2d7bae82db.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.21.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5909b01d85d22148a806f4c6674355e6a146f8a88ce28f98b64b26a27f27c854.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.21.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_effba5e1d64fb41643c1f559d28c3ae99426665eea41489917cf27295adc40ed.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.21.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_49187182e2d3f099a20b6e556d1338a48f05cabc4144658f73f0a9acf136abda.packed",
"scales": "t_49187182e2d3f099a20b6e556d1338a48f05cabc4144658f73f0a9acf136abda.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.21.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_380a3b48f153f13d38a61d1ed012c8de6695fb6befeec5d7f9f7542f2e85dc26.packed",
"scales": "t_380a3b48f153f13d38a61d1ed012c8de6695fb6befeec5d7f9f7542f2e85dc26.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.21.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_26107ed142536b5965ceaa85a8e494a2b68da3301d4f03a7f710b86ac1141509.packed",
"scales": "t_26107ed142536b5965ceaa85a8e494a2b68da3301d4f03a7f710b86ac1141509.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.21.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ae33624c03be2df95634595fc11ac5f8a98ec0999f0efa26093bd3d43a88953a.packed",
"scales": "t_ae33624c03be2df95634595fc11ac5f8a98ec0999f0efa26093bd3d43a88953a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.21.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f2ffeaf5e5452905a0e48eb5886226df6707c2ab926bcae899d71fb89265b17b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.21.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_afa50551d026f8a7f8ab462583d4032403e11c954aef9eb1088af3b9678b8a7e.packed",
"scales": "t_afa50551d026f8a7f8ab462583d4032403e11c954aef9eb1088af3b9678b8a7e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.21.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7e380bda5ccc81e6f23dab9390767356d5ceee2bed44ad3f7f7f525dd038805f.packed",
"scales": "t_7e380bda5ccc81e6f23dab9390767356d5ceee2bed44ad3f7f7f525dd038805f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.21.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1ccfd73bb49b7a9f8b649d9923df030e678991015f689541a3452b48950ec0bf.packed",
"scales": "t_1ccfd73bb49b7a9f8b649d9923df030e678991015f689541a3452b48950ec0bf.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.21.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9dfb640307e5aaa1d194284aa4e4fd159f19c9e541b95c8b336c6fdaae3c4099.packed",
"scales": "t_9dfb640307e5aaa1d194284aa4e4fd159f19c9e541b95c8b336c6fdaae3c4099.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.21.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6a315d7eacd1aaab81b3aacf18f9e418c3ced23e87a7a3a2c5ac5465a6a75800.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.22.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_457ce4a20fe5504b725dc13b2415f401367a196bf7cc500462daaf8f92d69d7f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.22.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_528fe9070f2b01b60efddacb90869d91c3ffddf3afad66cf996ada0a032ab450.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.22.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b576cd0b1c496766f428c0ff6dd8331a4ba128439721b2c3e41a1feb3117b7cc.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.22.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_52c7fba4a166744e1dde8854f83b9b397004981decbc7077db69d960cbf927a2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.22.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7b63e5ccb026fd3fcf8cc9e9cf61ef8f4610cb189c6971d1765f4008fce47cca.packed",
"scales": "t_7b63e5ccb026fd3fcf8cc9e9cf61ef8f4610cb189c6971d1765f4008fce47cca.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.22.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_dd4de6c336472c90a8caa628c42f4fcd54150962fb77c5eee30686d27a012083.packed",
"scales": "t_dd4de6c336472c90a8caa628c42f4fcd54150962fb77c5eee30686d27a012083.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.22.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4a57f7a6f8021a4969e1158dcc913930565f3862497dce1f872ea3456be6b1b0.packed",
"scales": "t_4a57f7a6f8021a4969e1158dcc913930565f3862497dce1f872ea3456be6b1b0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.22.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_51f5eb24277f3c5990e681932c3611826ab9ed73c554bce578197cd5bcfd41ea.packed",
"scales": "t_51f5eb24277f3c5990e681932c3611826ab9ed73c554bce578197cd5bcfd41ea.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.22.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4e7a47e0f209908d62a12566793d1442a747eb787740cfcfabc26f2a00b3ab88.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.22.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7dd5d69735da2a3cc39286af2bd4d4733dca7c6e87c1fbfd3eef1115eec1bd8e.packed",
"scales": "t_7dd5d69735da2a3cc39286af2bd4d4733dca7c6e87c1fbfd3eef1115eec1bd8e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.22.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ccf0762bd333c8c4ab7c1b2ef3b164d87e62de832ed3acd6467cf15dfdcf4022.packed",
"scales": "t_ccf0762bd333c8c4ab7c1b2ef3b164d87e62de832ed3acd6467cf15dfdcf4022.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.22.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_742129995484cc86b4a4845cf4000ac51f9c2769f01f4cafc3489a524a252fbf.packed",
"scales": "t_742129995484cc86b4a4845cf4000ac51f9c2769f01f4cafc3489a524a252fbf.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.22.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_13301fcb083e018c3f9d362ec0454b7229e60bb9a2cdabd644e2391b529a629c.packed",
"scales": "t_13301fcb083e018c3f9d362ec0454b7229e60bb9a2cdabd644e2391b529a629c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.22.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_65d263d59a6ddb245a34b73d526ad6016df4cfbe3a7a87a2dcf9a79b2de12ab7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.23.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f16cb3d76666a65ccdffb06d541cc697731289aa8c68ccd01ddea37492363163.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.23.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f30bcef47327021502f90858ff2def96088da648dcd6fd2fd4361731fb850a36.packed",
"scales": "t_f30bcef47327021502f90858ff2def96088da648dcd6fd2fd4361731fb850a36.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.23.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6434d8ce1554455be93a9062c946fc4dce94f9b983e102615ee5ce470339ad94.packed",
"scales": "t_6434d8ce1554455be93a9062c946fc4dce94f9b983e102615ee5ce470339ad94.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.23.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b03a11715df4aea995623fee120df283890b559f1e4c0f5b3a26700103045732.packed",
"scales": "t_b03a11715df4aea995623fee120df283890b559f1e4c0f5b3a26700103045732.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.23.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_bfb0f19ae0da4c637e5df6eae8da87a174270275c6f6caafde68606618a49419.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.23.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f0a4d8cfa4f92ec0c3c622188b502ba91ad5c5f5a677660ea77d9ae27cbf579b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.23.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_917c9af98c515c23de39968b6ad7235ea198089ae225b88b54ae5b9b23da741e.packed",
"scales": "t_917c9af98c515c23de39968b6ad7235ea198089ae225b88b54ae5b9b23da741e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.23.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_24a7e2cb57b7b2b26c503435aaf77bab0ac1264484019c554bcbe38d549ef549.packed",
"scales": "t_24a7e2cb57b7b2b26c503435aaf77bab0ac1264484019c554bcbe38d549ef549.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.23.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_42e048e67ff980f78a82e60ff55192533faa91212581d3bf1c688b1674f44121.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.23.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d7f55ea0521c603349df90ad365d68b35991758b00268c080d258667fa5ffc91.packed",
"scales": "t_d7f55ea0521c603349df90ad365d68b35991758b00268c080d258667fa5ffc91.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.23.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c6ec59b02ed3ec649eca216d1f15b5ae97ca5760f7e7104c4539a940057d5c3c.packed",
"scales": "t_c6ec59b02ed3ec649eca216d1f15b5ae97ca5760f7e7104c4539a940057d5c3c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.24.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_46da3e2f6eca89cbba9b9b3629fe2d010dcb7d483274cd43d1ae9902da5043fe.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.24.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_21aec069388ada5f34d740bed97aabaebddc14581b6db77dbe91c92536641ca2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.24.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ca66da614dc87d3e458e167fe64f1e3997d498d5190518b52e9e30d432375ae7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.24.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9c4ab5db252ba6e70a6f6f405f1d61fbe00e5bef3209da9c3a0e9269c7b65504.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.24.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1fd69c21caf84f4e12d682208034515bbcac4060e5db8dab3c72d49e5efe87b6.packed",
"scales": "t_1fd69c21caf84f4e12d682208034515bbcac4060e5db8dab3c72d49e5efe87b6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.24.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0862eafd0f4e6695df023419f226b1c92e008a33628e4c14e35fb49b80cddafe.packed",
"scales": "t_0862eafd0f4e6695df023419f226b1c92e008a33628e4c14e35fb49b80cddafe.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.24.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_32f7c76d1684a50ab4f697770829faf2f0a969d42d612b9db8b8db1cdf3c0812.packed",
"scales": "t_32f7c76d1684a50ab4f697770829faf2f0a969d42d612b9db8b8db1cdf3c0812.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.24.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e8717c3fc01d52d2dc3577e8aaa4cd2901d29f5796d365b2ca7b0f6432ca5f2c.packed",
"scales": "t_e8717c3fc01d52d2dc3577e8aaa4cd2901d29f5796d365b2ca7b0f6432ca5f2c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.24.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b53df4a6384f01a04fcb43074fee890ffe8fd440d66fced98d7ff930412e2647.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.24.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_05df5484eae7ccd5b474d1e4d94720925319a1dd39f1b23b24e5e107ae90a697.packed",
"scales": "t_05df5484eae7ccd5b474d1e4d94720925319a1dd39f1b23b24e5e107ae90a697.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.24.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_90c822c7cce33a95f6a53731610ca8840e4efe80f9f7a74de3aa999a58493d04.packed",
"scales": "t_90c822c7cce33a95f6a53731610ca8840e4efe80f9f7a74de3aa999a58493d04.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.24.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4c641a4e4a25963c320a62913b8a918dc800c42c7e48184ac411c74575a6382e.packed",
"scales": "t_4c641a4e4a25963c320a62913b8a918dc800c42c7e48184ac411c74575a6382e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.24.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9b157af2dc6b6c2e276e44005d20d22c0fd74d9f331f1f625e1ddb83abcf83ed.packed",
"scales": "t_9b157af2dc6b6c2e276e44005d20d22c0fd74d9f331f1f625e1ddb83abcf83ed.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.24.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_566bc2668229c588a98ab901d06fe0cda5111cc05d447f348d5522e83158dd4f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.25.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7647ba7a1f8f1e70a42a2449a5eeb350a61ba37cbee18e5d88bf08f10ac43fe3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.25.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4655eee0ba8984eb460a47a8aab3b245c4e431380c3bb8deac71e1e0c8c04b6b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.25.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d9f6ed612081551b8387e8a70e3b5d00472a471fd0cb3ba23b893c11a6dc5f3b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.25.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_25cd39765c898efb98b188631cfc65d2fcc6e9697209d41647324196d2b8822d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.25.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2af5182c90fa51cdfc612bd22d4185e23c22eb9a59c8500a7d1525ebbdc3a8ca.packed",
"scales": "t_2af5182c90fa51cdfc612bd22d4185e23c22eb9a59c8500a7d1525ebbdc3a8ca.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.25.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ce4eeca740d0c02d8ff092e7594e434cabb8cebf537e712f5d6d019697e190a2.packed",
"scales": "t_ce4eeca740d0c02d8ff092e7594e434cabb8cebf537e712f5d6d019697e190a2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.25.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_159277d210238c944c9fe028588744629cfa5b11622002ef851feea9269b67e7.packed",
"scales": "t_159277d210238c944c9fe028588744629cfa5b11622002ef851feea9269b67e7.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.25.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_12ba3435d5f71722d94803a3ab1a749587a6472aaf0bc80317ad6042fdaf7196.packed",
"scales": "t_12ba3435d5f71722d94803a3ab1a749587a6472aaf0bc80317ad6042fdaf7196.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.25.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c5dbbc860bcc6b3ac6b10770d6fb5ac3858b040a77382a7f5c8d2f07ce6e941a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.25.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_052d13d251b4bf3300a60e11f5f1b6417e966af128ecb1f82dfeff529019b90d.packed",
"scales": "t_052d13d251b4bf3300a60e11f5f1b6417e966af128ecb1f82dfeff529019b90d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.25.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_337d9638fd71f153385298f8e93ec6ada2c997d1f5c4a8a2c6ad55c636ffffc2.packed",
"scales": "t_337d9638fd71f153385298f8e93ec6ada2c997d1f5c4a8a2c6ad55c636ffffc2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.25.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_701bee1b7aa676ee9ad89b6e906c2b87ef3c0e1a2154f5512b4d1b1368e41b0c.packed",
"scales": "t_701bee1b7aa676ee9ad89b6e906c2b87ef3c0e1a2154f5512b4d1b1368e41b0c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.25.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_66eb1cb5d1647bf7b71a10ee847b2d8f5bd8fe7ea0be40d0a18cb481ff5027c6.packed",
"scales": "t_66eb1cb5d1647bf7b71a10ee847b2d8f5bd8fe7ea0be40d0a18cb481ff5027c6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.25.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c63566b04f0f5742ccd0ad4b0e7ded794827c16ba4d256ed3ca6c30c91c2ee71.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.26.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ad970a85ee6d037e937bfa32dffcf893b4e77cea634ba9042c4766b6e869023f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.26.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_71ef4973d978fa143e3271be0a9d3ee67e4f0e8bc84e8db1b4fdcb03362eca18.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.26.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e1c32a329b16218fc420290eacb2583ff05b0702c5333c6fc40b6dd471ba2eaa.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.26.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5aafdf4f95935eeb7396ebbbb121ae3e5727a7773a713c855e1e21aae3c391f7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.26.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b3e4189e4bdbb79ee768acb7f407c23e46408df956d7e8362c58ff785532a2c3.packed",
"scales": "t_b3e4189e4bdbb79ee768acb7f407c23e46408df956d7e8362c58ff785532a2c3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.26.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5797d0b8c9f0703116fecdaf27144954300e806d7883181e3696a4a063863f5f.packed",
"scales": "t_5797d0b8c9f0703116fecdaf27144954300e806d7883181e3696a4a063863f5f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.26.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f784eca95fb41c9c7ed0791c56f10739e245ac4b2c4bbde2dbaab4875a7e8b73.packed",
"scales": "t_f784eca95fb41c9c7ed0791c56f10739e245ac4b2c4bbde2dbaab4875a7e8b73.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.26.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5e0c3be819b80ff964ad6dc84fffc51f5059a21994206a2112882a2cbdc8b67d.packed",
"scales": "t_5e0c3be819b80ff964ad6dc84fffc51f5059a21994206a2112882a2cbdc8b67d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.26.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d0df14c255eb90c65375d9ff6facfcf74b0ea7996e4b69522fc63bce76d34773.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.26.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ae5c47b7df7283b0217d1c72b03540c816f44512fc787f8faf98149a0e0f3692.packed",
"scales": "t_ae5c47b7df7283b0217d1c72b03540c816f44512fc787f8faf98149a0e0f3692.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.26.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2b7a68f8adbfe8a4cd221b29ee1b4118ef80137d960581999fef82df29b2b18e.packed",
"scales": "t_2b7a68f8adbfe8a4cd221b29ee1b4118ef80137d960581999fef82df29b2b18e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.26.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d5c633164f8f33b91f25edce5a4c855e362e2c2ad1c56578473748230bd3236a.packed",
"scales": "t_d5c633164f8f33b91f25edce5a4c855e362e2c2ad1c56578473748230bd3236a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.26.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7a09029559636895cbf3a2abf3c7c6a48a90afbdd257d4cff5cd79fed72bdd8a.packed",
"scales": "t_7a09029559636895cbf3a2abf3c7c6a48a90afbdd257d4cff5cd79fed72bdd8a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.26.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6cc2c8969b2884f5c6d81449faa1f2539d775a3a391b792ca21df5f9dd5dd58f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.27.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_dd6b05968984ab6d2ac657483673131051ae5339402abc89083946215eb8efea.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.27.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f56add5f2c2264d277928b3bb966f6f686b54f8eb57231b372f6a5e9640f0fe2.packed",
"scales": "t_f56add5f2c2264d277928b3bb966f6f686b54f8eb57231b372f6a5e9640f0fe2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.27.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fc6480027d4c3efac71d06274451caf0d1842e3dd8b6c672c508b8f7657c5afd.packed",
"scales": "t_fc6480027d4c3efac71d06274451caf0d1842e3dd8b6c672c508b8f7657c5afd.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.27.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6330fb174a7c2b94de160c6bd31f03bf13e3fa3db2887b6d85d100394c081e06.packed",
"scales": "t_6330fb174a7c2b94de160c6bd31f03bf13e3fa3db2887b6d85d100394c081e06.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.27.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0c1ea3e7a615deba47247d8390e3e7910213ae10fb3be4ab2c12db872274054a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.27.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_34f56a95c93a6c6b8bc70052b8aed877ef963570824a95f7183b19186aaa67ba.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.27.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_78fed31e9deaa6399af4bfad7119bea9b819e0719460311cbd764e2e94535014.packed",
"scales": "t_78fed31e9deaa6399af4bfad7119bea9b819e0719460311cbd764e2e94535014.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.27.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5b704e95b7f9e195c8b2378133d121b800ff9aa7ffdfee7e8f19d9d32646eea4.packed",
"scales": "t_5b704e95b7f9e195c8b2378133d121b800ff9aa7ffdfee7e8f19d9d32646eea4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.27.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_97327678f93407e1d669bbdade1cd7261e12b9cf941154d637124b52ddc40cfb.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.27.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4b39d09277fc60891faa095f13d3e33b999fcac10f3ed2582e4644c8edfb55c0.packed",
"scales": "t_4b39d09277fc60891faa095f13d3e33b999fcac10f3ed2582e4644c8edfb55c0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.27.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f43cf2c5e36ae930f30d0711b9ff06bbef51aaec639e7e5f7b6ee078c26b418b.packed",
"scales": "t_f43cf2c5e36ae930f30d0711b9ff06bbef51aaec639e7e5f7b6ee078c26b418b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.28.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_13ca319d87e953ad3b8f4d9854f4e1aff2c3844d8533a04974b362a0150adf73.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.28.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c945ec091f1355c2d82e47e2fd6362c0db2e46fcfd67f498b06d18f4b70bfaa2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.28.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e862b21c54be13c55aa908f90fccf517053230b261844e15a518c0f7e486675f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.28.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_03a09e96f64a520ffd0524d25592de1582b67d0cc571f78260e1b28ff46aa62b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.28.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_63d8e65426678101dbc8bc261fa6767c1a954386e0eee3593112d764e390125b.packed",
"scales": "t_63d8e65426678101dbc8bc261fa6767c1a954386e0eee3593112d764e390125b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.28.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8375843b35ea6c8b810244f531f60dfa23ac9c268be4c81bb219ac6d92f67397.packed",
"scales": "t_8375843b35ea6c8b810244f531f60dfa23ac9c268be4c81bb219ac6d92f67397.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.28.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1e23b37e946ae89ff29d71d287967ed256049b569dc664ca9d6ce69e31193d7b.packed",
"scales": "t_1e23b37e946ae89ff29d71d287967ed256049b569dc664ca9d6ce69e31193d7b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.28.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fd8a3c3cf66208e9756d57cd22c39292974adc2ab0a9fd5a527f861606d3bbb3.packed",
"scales": "t_fd8a3c3cf66208e9756d57cd22c39292974adc2ab0a9fd5a527f861606d3bbb3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.28.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_2582e597329ec44b7be140d70ec8a35b84408e5f36d2fdfb036f8e111543d5c2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.28.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4f8d5e6caf166af5d28589acc677a5bc609aeed89d1a525c3596a0d6b32febd5.packed",
"scales": "t_4f8d5e6caf166af5d28589acc677a5bc609aeed89d1a525c3596a0d6b32febd5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.28.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_10d6fc3e8e6f584ae07a043a1c941811431396f321dbef9a26e6e144a2173493.packed",
"scales": "t_10d6fc3e8e6f584ae07a043a1c941811431396f321dbef9a26e6e144a2173493.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.28.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_316873871ca336d335c4d082ffd2679ec80e42c9a6e9e6b37cf01b2f0e110174.packed",
"scales": "t_316873871ca336d335c4d082ffd2679ec80e42c9a6e9e6b37cf01b2f0e110174.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.28.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0eac0e19afbee2bac656f9e28890bacb45d34c25a3c9a6910fcaa828269085c0.packed",
"scales": "t_0eac0e19afbee2bac656f9e28890bacb45d34c25a3c9a6910fcaa828269085c0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.28.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9d75091707b2b54beee3ec1503b9a2d7c21a6d69229be812f03022c48d3b1cb6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.29.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4e09b2106a5aed7cee5c919cf1a6b84f9143b1f4924d757aa55dffd50b914919.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.29.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_58a0ba467b24c00f0f32a5733f590c34d55518709e022d6b6e8035403a2d038f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.29.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_353a4cb829df82b5c64c72eecaf87884486b940fb50a80dc8af3fe8f7811827c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.29.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6c2986f5a2003c987bc419908170a13e9c906b4e6473150332070f345db257cb.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.29.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_03f136ec3957d6650f4f4c48580fb3101d0f26823e14e0f4e61c656b3ebe3101.packed",
"scales": "t_03f136ec3957d6650f4f4c48580fb3101d0f26823e14e0f4e61c656b3ebe3101.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.29.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_54e8fb92987ed2dae76f1f048b55939b8f8d3036a1868d978f527a93182bfbf5.packed",
"scales": "t_54e8fb92987ed2dae76f1f048b55939b8f8d3036a1868d978f527a93182bfbf5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.29.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f7fe51c3ef01491dd232e5fee3ed9d8c6dead87acdf12d19a81e963e21885571.packed",
"scales": "t_f7fe51c3ef01491dd232e5fee3ed9d8c6dead87acdf12d19a81e963e21885571.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.29.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6e10bb0d1424d6b86b448dd1dd414adf112a6cd8e83661915049d3a79ee10715.packed",
"scales": "t_6e10bb0d1424d6b86b448dd1dd414adf112a6cd8e83661915049d3a79ee10715.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.29.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_97cae57325eccfb86316f9461df2f42b1d3fc6793c50995dd835e47da317e9ff.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.29.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_289be60362e2b84aa458482ecec5fc1c8f2b7b231d7c64d925091e6cf45116ee.packed",
"scales": "t_289be60362e2b84aa458482ecec5fc1c8f2b7b231d7c64d925091e6cf45116ee.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.29.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e7c937dc2f96a18ca99e1039a83d8b3c31f8ce64a883902a6d8b630d098697f3.packed",
"scales": "t_e7c937dc2f96a18ca99e1039a83d8b3c31f8ce64a883902a6d8b630d098697f3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.29.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f4e5170808cd0857ad7fa4b65472a96534b0ec4e9e81dd015e494e862b419cf4.packed",
"scales": "t_f4e5170808cd0857ad7fa4b65472a96534b0ec4e9e81dd015e494e862b419cf4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.29.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8937f2c9f0f46ff510a0644e3300e04a9cc64a6abdc359859f96355e0a42a59d.packed",
"scales": "t_8937f2c9f0f46ff510a0644e3300e04a9cc64a6abdc359859f96355e0a42a59d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.29.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_2ae9ce48c37e88b95f671b027d7dc3a40f4b0f730e89950f66fa1259645e419e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.3.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8c60a78c20278c3791625434ab020c1fc2331d3f7e4f3373b7a4e9bc39e5605b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.3.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3c46b37a56cb62f419dd72bccb48c39d701ffccaf379e9d572c1589c8221861a.packed",
"scales": "t_3c46b37a56cb62f419dd72bccb48c39d701ffccaf379e9d572c1589c8221861a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.3.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_695861da6fe2f6767324694521dc4a2ac23b0f9a8268ad0eba1e911a83bc2ca5.packed",
"scales": "t_695861da6fe2f6767324694521dc4a2ac23b0f9a8268ad0eba1e911a83bc2ca5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.3.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_541de8561dabb83e20d7f6367ecc48fca0d69a42cbb3724d57b20b8ca076aa96.packed",
"scales": "t_541de8561dabb83e20d7f6367ecc48fca0d69a42cbb3724d57b20b8ca076aa96.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.3.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_aa6ecb7853338ab1906076e2fb36a46275fffa475d828294906566239c900d7b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.3.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a0bb1fd73d77d594d23f464d52915e1a5010a845332e746523a0486b398f7a91.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.3.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6c5e51490357d3b63a7eae52f04f41418cd3ae21e4da98adfad8c9dcd3c7d0b3.packed",
"scales": "t_6c5e51490357d3b63a7eae52f04f41418cd3ae21e4da98adfad8c9dcd3c7d0b3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.3.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1d7ac0af0b21deee648e09a2acd6963775f90c4bc431ec2003568f61ef71b84e.packed",
"scales": "t_1d7ac0af0b21deee648e09a2acd6963775f90c4bc431ec2003568f61ef71b84e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.3.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1907f8d0e963c3fcb2dd8112dd13bc5ab6e4edc66de768304a5ed00ba870577f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.3.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_655b72e32ae4348f342965ae96a659892803474dc3afab5eaf37bd23da7b68f8.packed",
"scales": "t_655b72e32ae4348f342965ae96a659892803474dc3afab5eaf37bd23da7b68f8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.3.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3e3651fd47363cffe2cab91664acb1743d559b0eb744197cea09f06cd5965c20.packed",
"scales": "t_3e3651fd47363cffe2cab91664acb1743d559b0eb744197cea09f06cd5965c20.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.30.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c14b1c3a83c4ec971fd7243591ed47a2aeae34499fd8b71279d9b7179b258efa.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.30.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e2e5595ac32f6efb815156d4d983cf51541bf11ae93d684a190fea0d32700d74.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.30.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_2423004cb56628fbe7089e5007547fbfbb366b5e2f232680709c2affd6e3eed7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.30.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_519a2d3313324a046ec05a554a0b151a1828019c65a59060ef72ff6c845e3715.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.30.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a5c71c203f1facb8e2a7c4e8604ed5abb41fa41a107add32e96a786a0c0b736e.packed",
"scales": "t_a5c71c203f1facb8e2a7c4e8604ed5abb41fa41a107add32e96a786a0c0b736e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.30.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_74f3af89183e10c476c5ffff75db61a1e57702ca5e7d8f653f4dc22861455f4f.packed",
"scales": "t_74f3af89183e10c476c5ffff75db61a1e57702ca5e7d8f653f4dc22861455f4f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.30.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a7e1b8438b4861b8d575692cd7fac3c6bc17ecb2a168f20335cd3d31c4c23650.packed",
"scales": "t_a7e1b8438b4861b8d575692cd7fac3c6bc17ecb2a168f20335cd3d31c4c23650.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.30.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8b7b3be000543ce33d8805c027cb76340e018cb82ed36a5f52affc63ccc8c477.packed",
"scales": "t_8b7b3be000543ce33d8805c027cb76340e018cb82ed36a5f52affc63ccc8c477.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.30.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_2ddad799005b8cd8e268f2a9b0ffd25078e946ed853627aa3615629c8fd44fa9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.30.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d19f3d7caaca2127049d34cd11e2ab48fc4b76399618a93b02e2af57212077b4.packed",
"scales": "t_d19f3d7caaca2127049d34cd11e2ab48fc4b76399618a93b02e2af57212077b4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.30.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_07831040e835db30d3a0c4c4a75d1b50cc5fbcda824def0dac42d583cc9a3028.packed",
"scales": "t_07831040e835db30d3a0c4c4a75d1b50cc5fbcda824def0dac42d583cc9a3028.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.30.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_686ac60b9b99046cf8b2de98d6797ed3fdaa29ad48fb1bde168d5a86725c5bac.packed",
"scales": "t_686ac60b9b99046cf8b2de98d6797ed3fdaa29ad48fb1bde168d5a86725c5bac.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.30.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_df5ebfa5ea76457793977b37f49a4d437a93cb8f9763a4b268274537d5d91842.packed",
"scales": "t_df5ebfa5ea76457793977b37f49a4d437a93cb8f9763a4b268274537d5d91842.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.30.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7de53db4e1c017ed024cb15555b75967744f43c6692602d67b3c46a3d1312374.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.31.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b79c0a9c2ab33b42436dfcd002c501c615830ca888014af91de444d392180b23.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.31.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8d035ab644f47adf4676aa3e20c15a30fb91aa6b6d725c47868739cea75052a6.packed",
"scales": "t_8d035ab644f47adf4676aa3e20c15a30fb91aa6b6d725c47868739cea75052a6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.31.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c9bbdc882a2fe9cb74d52a9a396b9691327482adeee261193d3b806fce508e61.packed",
"scales": "t_c9bbdc882a2fe9cb74d52a9a396b9691327482adeee261193d3b806fce508e61.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.31.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_71d352d091a770789b672783466b353b572e8870347f20416c1c4565fb512bd8.packed",
"scales": "t_71d352d091a770789b672783466b353b572e8870347f20416c1c4565fb512bd8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.31.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a8b2764d4aca7b97b258a8e07d36ffec419d5353844725a8254513bccdeac8b9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.31.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1eee16ebd116b905e33675a841f362665f300c816a88b78460ec5e7f2c254fff.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.31.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0c5fe40c506c6cbf3013091094a19d5644957986a78e585d5df835a84e344082.packed",
"scales": "t_0c5fe40c506c6cbf3013091094a19d5644957986a78e585d5df835a84e344082.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.31.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_af176693145b23c7c5f66de71de9d4ba7590d55d21fb5fefd9a66d15b3000fbd.packed",
"scales": "t_af176693145b23c7c5f66de71de9d4ba7590d55d21fb5fefd9a66d15b3000fbd.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.31.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_fddc1a6dd2ca4ddef458ea92a51e22c0535b861fd2fd5c924b49628e2274ce92.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.31.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f7cff2e815f7a27fab6cad03eb7bdb6c5979b44747cc052408247908538d1254.packed",
"scales": "t_f7cff2e815f7a27fab6cad03eb7bdb6c5979b44747cc052408247908538d1254.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.31.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c774d5ccb5cdfb6abb406b2e1f8ce7a51c3c9c5c4829c4f4f205ac30f195a51d.packed",
"scales": "t_c774d5ccb5cdfb6abb406b2e1f8ce7a51c3c9c5c4829c4f4f205ac30f195a51d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.32.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6a6f230b2db37979fcce5c4b0989a3b4cd2a7101f569d9dd2bf2be6c55ea5c13.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.32.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_44605a3427a0480108aa11034aeaa4f0ad2668c5fd4f8957acd7ec930f2d510b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.32.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_762b9628ddf836e3a49cad3171421072bb18326627d6173cefc291f94234bb16.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.32.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_56e2828fc186d3c1a09e9602d3a205e32607f2174dda7f6f9e5c1b8944ea05ea.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.32.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3f66a48911d797d8bd4cb8e7d920a47eb5fb6ecb4ebbffcf5839f1662bda9f85.packed",
"scales": "t_3f66a48911d797d8bd4cb8e7d920a47eb5fb6ecb4ebbffcf5839f1662bda9f85.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.32.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_71a1a4df4b33f2770c3e84332e83e790e1cfa5d9a0e1f61987198c7240ae2f34.packed",
"scales": "t_71a1a4df4b33f2770c3e84332e83e790e1cfa5d9a0e1f61987198c7240ae2f34.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.32.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5ea0471a4741c101cadac55c5c9f5d389ea8a8b48bd9b387e12f4e0fc9d4751d.packed",
"scales": "t_5ea0471a4741c101cadac55c5c9f5d389ea8a8b48bd9b387e12f4e0fc9d4751d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.32.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_444145bb525031e6f571d49e7c010a145858204ef404850af142977e28ef81d4.packed",
"scales": "t_444145bb525031e6f571d49e7c010a145858204ef404850af142977e28ef81d4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.32.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a7fd767282b50015e4800a93c9a6db1a622fa4cb8076252c8e400144e1d5e1e0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.32.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d1738cdb85bd21ef0a73a3e8599a6c907ffea6b3f18ac85a568b3bea0b829ae6.packed",
"scales": "t_d1738cdb85bd21ef0a73a3e8599a6c907ffea6b3f18ac85a568b3bea0b829ae6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.32.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9847943aba5f40c3d5d96cb01f081c1a3db445e7342d2fa158efdc9bf0a306ac.packed",
"scales": "t_9847943aba5f40c3d5d96cb01f081c1a3db445e7342d2fa158efdc9bf0a306ac.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.32.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_caf3cfafee858babfc5b28bd10108ea4ed26505b466546f7972f2b1164507024.packed",
"scales": "t_caf3cfafee858babfc5b28bd10108ea4ed26505b466546f7972f2b1164507024.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.32.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_95fc0135592f35dc2bd83ec06013010b1ec33f0b4bdc60990fbad5fd4225ec8d.packed",
"scales": "t_95fc0135592f35dc2bd83ec06013010b1ec33f0b4bdc60990fbad5fd4225ec8d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.32.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_58a22f437d0a9141067a7d6063f4d75c8420a5093bb3e9fc2037c76fbdf114ff.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.33.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_054ea5eb39e36c99649d930fbeed1be18f276feacbbaefc718e5c97c02f24dd8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.33.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b5495de46c1ad06adc9f48d56e13024c133319c8109a80e003b14158dcf7f804.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.33.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7cdc28eb1a6546f0c6a5b265a700621f0908a14436677444f92f102b7a65817c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.33.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3ef17800b836ccce67ce96a56c548557ece46095a1708c9009b8e313d168811e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.33.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3e3feb76d5c62144e27e936f7b8c53c122078e3ce44f1883401c0ad6306ed810.packed",
"scales": "t_3e3feb76d5c62144e27e936f7b8c53c122078e3ce44f1883401c0ad6306ed810.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.33.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c4e53a37c6b877d173ab17de17ac08b7d72d3694708a07fc67e0df4a7b5c4110.packed",
"scales": "t_c4e53a37c6b877d173ab17de17ac08b7d72d3694708a07fc67e0df4a7b5c4110.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.33.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_234e6b29225fcba2d1a1efb5a77cd449d1c8230d72a2d3c0b162530bfae7861b.packed",
"scales": "t_234e6b29225fcba2d1a1efb5a77cd449d1c8230d72a2d3c0b162530bfae7861b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.33.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_33ce9569deeb4be50f0b5f7341bac673a90dadc906f1d191f1ed6d7af521ff5f.packed",
"scales": "t_33ce9569deeb4be50f0b5f7341bac673a90dadc906f1d191f1ed6d7af521ff5f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.33.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_61438fe2e5f5d1c8851228335515edb9b4553c9a29db8288a3d5ed966f1cc040.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.33.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8a06d7b2a2c99fb6cab4e6afd3de1bdd7c05ebe1861fb7519514068fe41c6c2a.packed",
"scales": "t_8a06d7b2a2c99fb6cab4e6afd3de1bdd7c05ebe1861fb7519514068fe41c6c2a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.33.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0dc28ea532a3620d8f5d421c808d7c171265b04e515ee8be6858138af91be737.packed",
"scales": "t_0dc28ea532a3620d8f5d421c808d7c171265b04e515ee8be6858138af91be737.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.33.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9694e2f6a3c3276eb6d32148fc8bc60443b6c7bf2df41d70392406f6c5c54d06.packed",
"scales": "t_9694e2f6a3c3276eb6d32148fc8bc60443b6c7bf2df41d70392406f6c5c54d06.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.33.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_91dc1f7345a63ef2ba75974e3fc75a52993d5571ddfc2199f821f53a391dcae2.packed",
"scales": "t_91dc1f7345a63ef2ba75974e3fc75a52993d5571ddfc2199f821f53a391dcae2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.33.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_07ca3399f070265795d0549dbab9ad501961b0221a9dded84876d76800d09933.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.34.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e27d9aeed25df126fe8d26844bf13db0ea29c5c49d7d87783bb1822e20559fc7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.34.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_63eec75b110493cf1c0ec667941d2f3e604ab9ead2969a123cace34c11b39769.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.34.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_01ff209510371e83536aee14a35430b2525f1473cef84f00e225666d80610745.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.34.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a53f9a5b48a554576725c9da2b9c560f655cec2f52a2c5e4b8abe16a34e8b6f7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.34.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ed8db3c3478636833bea588c98752f0ce2f13ccb3726b49c574c087d8f08e77b.packed",
"scales": "t_ed8db3c3478636833bea588c98752f0ce2f13ccb3726b49c574c087d8f08e77b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.34.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_83a3ab34adfee8f84264e529a0a9b24ab9441f505e78241939719ec860757da3.packed",
"scales": "t_83a3ab34adfee8f84264e529a0a9b24ab9441f505e78241939719ec860757da3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.34.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4566860a8735c920aed1041c631eea39aea56035cf7f9ebac2d0352b8bedde49.packed",
"scales": "t_4566860a8735c920aed1041c631eea39aea56035cf7f9ebac2d0352b8bedde49.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.34.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_62cb6b77d911b1fa701c7f1ab31a757e45e37c71abb784e86fb5e00d34a653a6.packed",
"scales": "t_62cb6b77d911b1fa701c7f1ab31a757e45e37c71abb784e86fb5e00d34a653a6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.34.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c4e515c4d9696c079925480c3dc8dd6261a01a40a1f3d2dd123382932a2e248a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.34.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7ac3f325960b431a9528ffc6f0c700a04638dfda83c94559e85c59cb1dace1c0.packed",
"scales": "t_7ac3f325960b431a9528ffc6f0c700a04638dfda83c94559e85c59cb1dace1c0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.34.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cfb61703d32cf2834eb2b4068b4070f33e2436535e0ba4af1b12b0fa2fb64f2d.packed",
"scales": "t_cfb61703d32cf2834eb2b4068b4070f33e2436535e0ba4af1b12b0fa2fb64f2d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.34.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2576c5cbf2127fe650030065930855fbe25dee742f32f1708a8d930c356b2bb2.packed",
"scales": "t_2576c5cbf2127fe650030065930855fbe25dee742f32f1708a8d930c356b2bb2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.34.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_aaeca45e3cbb3c635ba6b5c5be10a3b594e6abfaa252d0a9b23b6349a355622f.packed",
"scales": "t_aaeca45e3cbb3c635ba6b5c5be10a3b594e6abfaa252d0a9b23b6349a355622f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.34.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_13e02ccf1fd6319a17c45882592a81ff847148256960fb80512b7eaa980a5587.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.35.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0a5d18a53c3cf93eeaadfb4f59f0d762f791d6dad76c1bc7a40e206f8774b21f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.35.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3e7b002393c8233c1db8377e567fdfab771a106151f557b800b8ec99feebc3b8.packed",
"scales": "t_3e7b002393c8233c1db8377e567fdfab771a106151f557b800b8ec99feebc3b8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.35.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3663336c7f98f01286a49ac691a10b6ad474cefa867c14fdc2b6b87c9942e19b.packed",
"scales": "t_3663336c7f98f01286a49ac691a10b6ad474cefa867c14fdc2b6b87c9942e19b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.35.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_417e8980e85e4ab9e61d839cbf3679c46bcb07640e5e0c1805b60c63d9c7d49a.packed",
"scales": "t_417e8980e85e4ab9e61d839cbf3679c46bcb07640e5e0c1805b60c63d9c7d49a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.35.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8b307d0a70ef06b79814fe33d0867210f693086e8ac91f9984a99a22e3751559.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.35.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5e85453d416085e8e8c286ed5de79c0c4dc2caa8610b725f1eeca32e459a247b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.35.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6e9264b65a796bc26459cc8d9ded69d263d5d012eba50b3e320d01d0692c0bab.packed",
"scales": "t_6e9264b65a796bc26459cc8d9ded69d263d5d012eba50b3e320d01d0692c0bab.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.35.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_28e6c23fe52a6866c7528d8ce6f586ef27dcd602e5e29c922eea62be4ed48f44.packed",
"scales": "t_28e6c23fe52a6866c7528d8ce6f586ef27dcd602e5e29c922eea62be4ed48f44.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.35.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b21735922f8027c500786aec6569076a0b17311ddd8fbd218c1712c0fbc36574.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.35.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3b7ffb849bb37cbd8d4ff4c341baffeb1517e84d56b677a9120e6042e6b467ef.packed",
"scales": "t_3b7ffb849bb37cbd8d4ff4c341baffeb1517e84d56b677a9120e6042e6b467ef.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.35.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2c2c3eb75d06f797a204dc8622631c0f354543434306cc16efe6ff0e8ceb847e.packed",
"scales": "t_2c2c3eb75d06f797a204dc8622631c0f354543434306cc16efe6ff0e8ceb847e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.36.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e67be6aa4f103456df873fd846f2b0af8a221c8d1103c6bc8c4338e41817157d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.36.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a99ef810e19593975da95e6da97e4127c4c105f486714e764d26d5b347082924.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.36.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d49a790635c1248a7a59f04bab1b7d902a3d9390a47961b2bbd542612e3401d6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.36.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_bf82ff9139086369dfa21ff76d221353dd9de9c2447373dd9c8f605bba5223f6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.36.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f67d71647e5ab4daeb7649ad6c7220237fa5f4c19d0d7880fa6f3def74fe27b1.packed",
"scales": "t_f67d71647e5ab4daeb7649ad6c7220237fa5f4c19d0d7880fa6f3def74fe27b1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.36.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2f01f4af00fc09bb7445f82b50bb042263a69dd188fab160e5157533c1912750.packed",
"scales": "t_2f01f4af00fc09bb7445f82b50bb042263a69dd188fab160e5157533c1912750.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.36.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_04f25851e5a911e176243424cb8ae305f91058416753a2490846f6fea2057bff.packed",
"scales": "t_04f25851e5a911e176243424cb8ae305f91058416753a2490846f6fea2057bff.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.36.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f95d28dd16cb6ebed2cd8260016d65416fe6f7fafc89710158ec419c029c79cb.packed",
"scales": "t_f95d28dd16cb6ebed2cd8260016d65416fe6f7fafc89710158ec419c029c79cb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.36.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_26023a8baad987e247f338599bc090c607e799c18027f73dbdb07478d491329c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.36.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_98c213d7d25664917630fd992debdd05397239fa6405757d75c74d2ca04f543c.packed",
"scales": "t_98c213d7d25664917630fd992debdd05397239fa6405757d75c74d2ca04f543c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.36.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a019915245a6fc79ea82667167bbcb03df857b698222f9650cc249d5329dae0b.packed",
"scales": "t_a019915245a6fc79ea82667167bbcb03df857b698222f9650cc249d5329dae0b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.36.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_413e0eda4aad86db2599b8780de3bdca98cc579f07d46ca15dbcdb2bcfb3d144.packed",
"scales": "t_413e0eda4aad86db2599b8780de3bdca98cc579f07d46ca15dbcdb2bcfb3d144.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.36.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f97f8718f4771b99965f5dee38fe6d0c964cef3131dc6a3c22adb8da35b2555e.packed",
"scales": "t_f97f8718f4771b99965f5dee38fe6d0c964cef3131dc6a3c22adb8da35b2555e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.36.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a3cdfd3b88c7b2c15220bfc0f6407edaf48ca24167ac0e3f3b5b258187eefe3b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.37.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_79a9d66b880c236c72099a6987f107ea7835e1accf2e246aabcd61095555e8a4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.37.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a416b3b4d67055da0d00ee995288278a5d741cfa3a4b7649ff5df3dbd11a6e8f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.37.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5c68e596c9a00b8c83fd8f9f6637b9c12d4151ef18f27df23df7d3262d4dc555.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.37.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cac2123f270099c59736d5a8624d698ef7245b247e1aab291c760721296ae271.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.37.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5e584625c3132b242d7f32396b64a6f3ea188c36bd8b4b2b58ee7fbc1ca4809f.packed",
"scales": "t_5e584625c3132b242d7f32396b64a6f3ea188c36bd8b4b2b58ee7fbc1ca4809f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.37.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_402a38d007389cfb70469d73002828e44471655c2e1b06bb3c861a9d72fcb237.packed",
"scales": "t_402a38d007389cfb70469d73002828e44471655c2e1b06bb3c861a9d72fcb237.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.37.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a577cd0e93d0896e3d0192f0b61a448c7ce543df0c7935bcbcb7b6f8b29fd75e.packed",
"scales": "t_a577cd0e93d0896e3d0192f0b61a448c7ce543df0c7935bcbcb7b6f8b29fd75e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.37.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_91c8b96df0fa97fda1297c6c24ba176b41382017d99bac83bea47b202efa6735.packed",
"scales": "t_91c8b96df0fa97fda1297c6c24ba176b41382017d99bac83bea47b202efa6735.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.37.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_205c2026f0361bc09c85b4854fdd723f9bdcec90cdefb167dc76100f377b9c0f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.37.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_103fecc68bad5199697ab9335618bcf194ecb63151c166a4334a59ce3865a1fd.packed",
"scales": "t_103fecc68bad5199697ab9335618bcf194ecb63151c166a4334a59ce3865a1fd.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.37.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2edbe9a7139b2853deb9d2f5dce7b8a36ec8bdb6b918a0fba97d322164517659.packed",
"scales": "t_2edbe9a7139b2853deb9d2f5dce7b8a36ec8bdb6b918a0fba97d322164517659.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.37.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1aa99442221c6dbb05d7fc708ad11cbcc716f2e1b9f6f485dab65e374fbb5b79.packed",
"scales": "t_1aa99442221c6dbb05d7fc708ad11cbcc716f2e1b9f6f485dab65e374fbb5b79.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.37.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a753775fca8c21dd4ab03bb3f43f39ed31066fb19aada1ff092b9d49b00799b1.packed",
"scales": "t_a753775fca8c21dd4ab03bb3f43f39ed31066fb19aada1ff092b9d49b00799b1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.37.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8224f6dcdc19556065fdbd128ce46510bf2d944fed18215154961b4625188ede.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.38.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_eaddef1a8867e788f7b57dde25f792474275f48bc5e226f0ed393ab18cbf6f4b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.38.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_69a0fe5e2a0641a8824843f0cf71d23fe5d6588a271b344137aadaf9e049cac6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.38.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_bfad6904bceabc613ded9fdb77e3c46399db4ef0c2754dd980b64e21a7e276f6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.38.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_24cf0e2c43bd7581bd8536aae34243044d781ad6aa30857d2baf28836a1278a4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.38.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1dd026a8121d835f5e5c60e348080baeb6555917e587ce853ac70a65de4906a2.packed",
"scales": "t_1dd026a8121d835f5e5c60e348080baeb6555917e587ce853ac70a65de4906a2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.38.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_db6fd7739882c4663028b759dbb1e4c570e174b97f4c0e646db0fa5d67f62c4e.packed",
"scales": "t_db6fd7739882c4663028b759dbb1e4c570e174b97f4c0e646db0fa5d67f62c4e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.38.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_837c1073224c866f21f25bb9392f27265bb25ad320394ae56037d51c0c9e76a1.packed",
"scales": "t_837c1073224c866f21f25bb9392f27265bb25ad320394ae56037d51c0c9e76a1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.38.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bbdd95d559f83161a87d304ead2d2fb975b9a9c3fc5a62e4fbe2d41297608d5f.packed",
"scales": "t_bbdd95d559f83161a87d304ead2d2fb975b9a9c3fc5a62e4fbe2d41297608d5f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.38.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_41905f7fb459815e433db857fc113f651db8c9a22792675090ec9263fb2efeb0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.38.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_31dbd0c2b292f3ad4a4e8a4df15430a199f44e1b91b81debab4b8295fc8f8106.packed",
"scales": "t_31dbd0c2b292f3ad4a4e8a4df15430a199f44e1b91b81debab4b8295fc8f8106.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.38.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_58ed732ec2ec0534b09358f7ae7e17812b8d5c73852cda9d4cdc94fc4c27c4d0.packed",
"scales": "t_58ed732ec2ec0534b09358f7ae7e17812b8d5c73852cda9d4cdc94fc4c27c4d0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.38.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_83bfb4ecdfe7ebd45a105eafaca7440923b4f9cfb7fe09bc15b9784b6a5520d6.packed",
"scales": "t_83bfb4ecdfe7ebd45a105eafaca7440923b4f9cfb7fe09bc15b9784b6a5520d6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.38.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3c3fcb01e188064aea6a6e2f1f80e8d7254e675b20afdcda70723983a27faece.packed",
"scales": "t_3c3fcb01e188064aea6a6e2f1f80e8d7254e675b20afdcda70723983a27faece.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.38.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3795d40fe9e58813867888a2b59002af51fcd37b865515a0a2eef58416fb6e8f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.39.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8be3b4749cb6883b197e54c2fc6ac07cfa463e41605a7009c2c4cca189d9a92d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.39.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6c659ae3f91c64797d5d3327f943f50978b05f51ca2ff364d4666f965793c8f8.packed",
"scales": "t_6c659ae3f91c64797d5d3327f943f50978b05f51ca2ff364d4666f965793c8f8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.39.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3802b15847adf24164c4f4856d2fcc657b1cc2bcc3dbe8914b4571e651b6fa55.packed",
"scales": "t_3802b15847adf24164c4f4856d2fcc657b1cc2bcc3dbe8914b4571e651b6fa55.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.39.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_edfaef8b2249b0e3d48dff8eab3564e8d23debf9bfd58ec22095ec9fb6d2ef65.packed",
"scales": "t_edfaef8b2249b0e3d48dff8eab3564e8d23debf9bfd58ec22095ec9fb6d2ef65.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.39.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_11446f4a5d03341c9124eaa3a2a3733238260804cb4a25665e9c0db1d79dc953.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.39.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_daed4196bb1e360671f2481bb6523881311ad991efbd5139436b501e714ea15d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.39.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_72140eaf9b06d02f9d445acc6ca79ca67d3ca38086079a1e6aa897a0cc8839d2.packed",
"scales": "t_72140eaf9b06d02f9d445acc6ca79ca67d3ca38086079a1e6aa897a0cc8839d2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.39.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_28c7df426f8ed9ef09caf0d6156181e516e0e204dea1e7ee08dad5c1f103a726.packed",
"scales": "t_28c7df426f8ed9ef09caf0d6156181e516e0e204dea1e7ee08dad5c1f103a726.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.39.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c6c768f04e94e4f2e99ef10a55facad963bee268f33ea82ec96e665173d4c933.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.39.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_899a3d02ff705c0846e26e3eb77d214f0d7fa2a5e3ca329a96fdea4a52609be9.packed",
"scales": "t_899a3d02ff705c0846e26e3eb77d214f0d7fa2a5e3ca329a96fdea4a52609be9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.39.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_211904235cd04bb4d0de30fb39792db4fc07baa4424b885dd8925c4c145f15df.packed",
"scales": "t_211904235cd04bb4d0de30fb39792db4fc07baa4424b885dd8925c4c145f15df.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.4.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a637bd21af89685ddb88970c0195f83ad232719ea85cc91d8112e19f08f2a0f9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.4.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0a474c7e3e4a24e4af41ca1e240a5564f02264baee4fdd93d2de6f0d1cfc793d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.4.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ee4ea84b4b03b7e03b9ade8694278f9256cd9aff6bfe11680846a66a01295ef0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.4.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7666d2f33c0d14037ac1590f9c418260454ced025274b8223731a6ae86f640df.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.4.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b0e6ba16ed468f9171e54d66e08bcf5282c48439a3ab5a963d2efb2bbca4a21f.packed",
"scales": "t_b0e6ba16ed468f9171e54d66e08bcf5282c48439a3ab5a963d2efb2bbca4a21f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.4.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_41481c856f109a4e267911ef5ff52f60f245c481f1628b9e5579c3afed58152f.packed",
"scales": "t_41481c856f109a4e267911ef5ff52f60f245c481f1628b9e5579c3afed58152f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.4.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6c7bfe488fdeeb6de6ae4aa50c5cc954ddad7b850fa6f935cde054516f3f6850.packed",
"scales": "t_6c7bfe488fdeeb6de6ae4aa50c5cc954ddad7b850fa6f935cde054516f3f6850.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.4.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d9b5374cd7f1c59383987a70fa725dca8c1f57e77d8db57d1022531913db9985.packed",
"scales": "t_d9b5374cd7f1c59383987a70fa725dca8c1f57e77d8db57d1022531913db9985.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.4.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3a64ef2a0eb96df78bac60dddea62f55953d3bb7243316f586ff56df7875bb3f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.4.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2c6681a998a9ea8911f4f076323627f2b1a60466b8ba5bab767b8d1232052df2.packed",
"scales": "t_2c6681a998a9ea8911f4f076323627f2b1a60466b8ba5bab767b8d1232052df2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.4.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d0d828cf40f0a713181f83f3fc7b1c12c4811e2a86d898ca127d3dfdd59b0789.packed",
"scales": "t_d0d828cf40f0a713181f83f3fc7b1c12c4811e2a86d898ca127d3dfdd59b0789.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.4.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_af3af7bcd62a4c33648f47ed5580195b6cb30738ef8204a5132f5b81d8185c0c.packed",
"scales": "t_af3af7bcd62a4c33648f47ed5580195b6cb30738ef8204a5132f5b81d8185c0c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.4.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_25089b64a53062f563f35c8a1581d7554e166253edb506d1c8945382a9abe78f.packed",
"scales": "t_25089b64a53062f563f35c8a1581d7554e166253edb506d1c8945382a9abe78f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.4.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_abba2fab0750e9ec1a6425d1a0b4c4cee00f21fb3102f0cfc5b70302a0715984.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.40.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f8a58804d2ea463a509c0b58e9868624543b887960311323efecbc60a2f2fb48.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.40.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5d3e7f0ffa6ec4eed420914ec35b5e1509413eafabdc0517da5221ac039143d2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.40.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1d2c39271cd739ae75174b3f5efc2903fa335446446b31f9e02db45f60ef9289.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.40.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d4436f70cb4fb284a1c229c2d68c3c71012c4e5a3fec275829409db0c608fc35.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.40.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_aac5dcfd5063dc41e51358b4e0d68994838a861aa2f108d22b5756f05650aea5.packed",
"scales": "t_aac5dcfd5063dc41e51358b4e0d68994838a861aa2f108d22b5756f05650aea5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.40.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c29f1eed3520c69f3fe1a33ac8d890f58a30ec1625834f7c0dbcb57d38237344.packed",
"scales": "t_c29f1eed3520c69f3fe1a33ac8d890f58a30ec1625834f7c0dbcb57d38237344.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.40.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e1c324a1ef1b2fdbf8457154ced413396b82df3498e37de84a596ad48cf1d1b0.packed",
"scales": "t_e1c324a1ef1b2fdbf8457154ced413396b82df3498e37de84a596ad48cf1d1b0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.40.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bb09e5689238a17194c7c13a92f6f4460328b662c71ef628e6c61a6707b82d44.packed",
"scales": "t_bb09e5689238a17194c7c13a92f6f4460328b662c71ef628e6c61a6707b82d44.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.40.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_591cec416264dff095548e719de3e83889891e625182c6988907f4dc7ef0a183.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.40.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a34e9a153bb524c4a17c7627fee006ea5add3ad46624d36226a5a576a915b668.packed",
"scales": "t_a34e9a153bb524c4a17c7627fee006ea5add3ad46624d36226a5a576a915b668.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.40.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e8fb674f4a7e5776c8e2b2f57d04733b049b44ebe80e4714c6bc4da062e52849.packed",
"scales": "t_e8fb674f4a7e5776c8e2b2f57d04733b049b44ebe80e4714c6bc4da062e52849.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.40.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c814586423a785e030374a9da1b6e20bbe8752d1931ac370a3f447ae2a052f0e.packed",
"scales": "t_c814586423a785e030374a9da1b6e20bbe8752d1931ac370a3f447ae2a052f0e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.40.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2c2b3de896254d179a42397bf0ad934fb9625f09e2c722d62e2bb52234b9591d.packed",
"scales": "t_2c2b3de896254d179a42397bf0ad934fb9625f09e2c722d62e2bb52234b9591d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.40.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d7830afc7787b9addad9beeed5d17147f028d7ab447f206ed7ecfd2463e4946d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.41.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a57048b24162be0087302e3604e3b78c94a5a207c1da95c018bbcf648988d0f5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.41.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f68f35600d47bb8e9071fb7f456931dd07eab1ae367ce8ba1bfee47aee4d32a8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.41.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3c860fde2b40c3ab6ba317b6d6daaba1638e7f8a336e99729afe20d0023068e7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.41.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_78ab06b79b5e3e2b1142eb2d908ebef87b55815266cf62aec83499a0fe7cfb8e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.41.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_dc969ead0824881a8e990fa90998dc2a974096caed246e5e2e2605c5af9913ff.packed",
"scales": "t_dc969ead0824881a8e990fa90998dc2a974096caed246e5e2e2605c5af9913ff.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.41.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b2428c3c00b42d6e371e24581380b502f7574e8df65a9c3e524ddc681c63104e.packed",
"scales": "t_b2428c3c00b42d6e371e24581380b502f7574e8df65a9c3e524ddc681c63104e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.41.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0ad5162d1595636336ac0ba73fdb3141fb89df3f6322b9a3499291d38460f13f.packed",
"scales": "t_0ad5162d1595636336ac0ba73fdb3141fb89df3f6322b9a3499291d38460f13f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.41.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_25db42bd9ba30cdbd316292443e82af574818024c4bbde4f5686936805ab40e7.packed",
"scales": "t_25db42bd9ba30cdbd316292443e82af574818024c4bbde4f5686936805ab40e7.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.41.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6c843b6666c5ce2efc317240086de82da9fdd9a60df399261cb5aa50ddf4b88a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.41.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_faf7a5a6741314a1c00b9b20b9eab4a7a9961b46a55132961fae221f6f3a255e.packed",
"scales": "t_faf7a5a6741314a1c00b9b20b9eab4a7a9961b46a55132961fae221f6f3a255e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.41.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0e43ad8a2b4d826f874f661d28b678866bb0ca1b0e8a224c5a021a6b81738af0.packed",
"scales": "t_0e43ad8a2b4d826f874f661d28b678866bb0ca1b0e8a224c5a021a6b81738af0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.41.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2445115c1ee7f1039edd75e2c766415253389c867e705d486615109ceca1b6a2.packed",
"scales": "t_2445115c1ee7f1039edd75e2c766415253389c867e705d486615109ceca1b6a2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.41.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_caf29e712ca4c76fd062a8d7781adf0124d2d2b0860855e357b807c8012665b4.packed",
"scales": "t_caf29e712ca4c76fd062a8d7781adf0124d2d2b0860855e357b807c8012665b4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.41.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_69a862bff986bfeec1e4d0b9df0e8f120724f7fb3d69c34ac2963fe03d6869b0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.42.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_fe9ac59ffed0ae6f41db0a75fbf45c2698284443ab7057d0b9f3e59a09239bd7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.42.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_77cafb7f69f892f69b9d34a11c326fb9692356b707ead0c53a3a24048ccd43a3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.42.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f646ab4897a81900e89c04b53dda67c372241d5e4f1dbbf09035cd0b4571d583.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.42.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6adf8afb1c5dbc03098772ddca003df2aad667a6dadd2d949d027fc48008e79b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.42.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_041a1ef175cfce77492f8a229cf777823d008eb2dabf2a4d0cde44cc17ea2824.packed",
"scales": "t_041a1ef175cfce77492f8a229cf777823d008eb2dabf2a4d0cde44cc17ea2824.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.42.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_714cce05c2aca7f22b73ab2c6ecc322f8d1d3f03e5953356eb3b902528a97039.packed",
"scales": "t_714cce05c2aca7f22b73ab2c6ecc322f8d1d3f03e5953356eb3b902528a97039.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.42.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7df9474fd52e47235e1ca6ab51f2145abcf613d716f351d1a034fabb6a9c391a.packed",
"scales": "t_7df9474fd52e47235e1ca6ab51f2145abcf613d716f351d1a034fabb6a9c391a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.42.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_aae54ba42b7ee1ac27a71651a26efbb396946e909709152acf4ec11682ca1607.packed",
"scales": "t_aae54ba42b7ee1ac27a71651a26efbb396946e909709152acf4ec11682ca1607.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.42.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_60fdbd702558bfcae02568019ad9417a0cbfd86fc7aba13a2a7672471855dc63.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.42.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3923bca53b3cf2a0b351878d4aff222802e6192afb298a1314a41d3d4ee7640b.packed",
"scales": "t_3923bca53b3cf2a0b351878d4aff222802e6192afb298a1314a41d3d4ee7640b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.42.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cc69b637918a6f5832c05739922023d4e13cc0ef0e8a4a9991d271c37e188c1e.packed",
"scales": "t_cc69b637918a6f5832c05739922023d4e13cc0ef0e8a4a9991d271c37e188c1e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.42.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9ecdc2b97d124db22216b1b6005e03a0466096a7ec5653cb3e5a61003347061b.packed",
"scales": "t_9ecdc2b97d124db22216b1b6005e03a0466096a7ec5653cb3e5a61003347061b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.42.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b87f5ed67ae1476cebf9b6ce5662e17b2e405f2155a62ba21d12b85aa62f0f33.packed",
"scales": "t_b87f5ed67ae1476cebf9b6ce5662e17b2e405f2155a62ba21d12b85aa62f0f33.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.42.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5738d6ec7464299d91769c7f630a1d94f4c53d4cab2622317e6ca8e6d7db9dd9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.43.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_361be4e97acf29b8f23b483ed1de70ed2df1f2f5d5edba84869394837547b2aa.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.43.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_497f85ef7ad9ddf72f0619bf420eb750194caacdd5a7ea77e00ff719f12664e2.packed",
"scales": "t_497f85ef7ad9ddf72f0619bf420eb750194caacdd5a7ea77e00ff719f12664e2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.43.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ca6a0b0f147cdbb4a7d64942aba679267d13b8ab2620d70ced75f657fd4dc00e.packed",
"scales": "t_ca6a0b0f147cdbb4a7d64942aba679267d13b8ab2620d70ced75f657fd4dc00e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.43.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bd1da379be3db530faaea30801f1ad0b8bfb22ab96cadb64c61af977d2f66762.packed",
"scales": "t_bd1da379be3db530faaea30801f1ad0b8bfb22ab96cadb64c61af977d2f66762.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.43.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_21471fc0b6164b1b3707ac2e069b244d52cf2441032db8acd09397ec784aded0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.43.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_35f0785c4499dad75381246fd852b0cfa7d8054da182026bab7c901e494a2ce7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.43.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9087df1e6e2b4286efb4b8fa9d7fe81c3653f8703b8e01f00cb897568f3492a4.packed",
"scales": "t_9087df1e6e2b4286efb4b8fa9d7fe81c3653f8703b8e01f00cb897568f3492a4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.43.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_43d0c069651e2845faf0c5f135efa699554ed36d21c262400e3882cf5aa72500.packed",
"scales": "t_43d0c069651e2845faf0c5f135efa699554ed36d21c262400e3882cf5aa72500.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.43.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8ee7fdad13eb45457715aa85cb46baf6608406d5094c57adad3dd3572fe839de.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.43.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bea57099b5205e79071a7d1be7009f93afc594cb57179958a734fdf75dd507ee.packed",
"scales": "t_bea57099b5205e79071a7d1be7009f93afc594cb57179958a734fdf75dd507ee.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.43.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7f2a16df3ba5a18f81def7cb4f86218fab91a54705ec77394111881439e10e2a.packed",
"scales": "t_7f2a16df3ba5a18f81def7cb4f86218fab91a54705ec77394111881439e10e2a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.44.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_87672fc56b40ca00ec2f0ca045ac5da35ccfc8b219d8241a7d8b8ea1913a4971.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.44.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0c43cd90df002e117b5325c15cb59796d9b57a91a0595aa827a300bad458265a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.44.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5661d52d423b23d67eeb84860b4ff3fc0453004303ca07a45561750319bacf5d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.44.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_abc4599512ac7fbd2228f00d48253fdd0c554c37003c162af709ed23f80ec5df.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.44.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6c0c686435c4069c4a0bef4e7c686f492ae7443ea63bf0118034e4a19b533c41.packed",
"scales": "t_6c0c686435c4069c4a0bef4e7c686f492ae7443ea63bf0118034e4a19b533c41.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.44.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f8707dc60986ba46955608fd7575ba12dca890d157404f008d18dc4479325b61.packed",
"scales": "t_f8707dc60986ba46955608fd7575ba12dca890d157404f008d18dc4479325b61.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.44.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b5f2135381bcfdadb357b809e460b87c313929c97d098b19cfacddd6dce94b76.packed",
"scales": "t_b5f2135381bcfdadb357b809e460b87c313929c97d098b19cfacddd6dce94b76.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.44.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0655da342eacda35dd144f860c7981c8a7709e4bd79cda309d16a4133af1ca1c.packed",
"scales": "t_0655da342eacda35dd144f860c7981c8a7709e4bd79cda309d16a4133af1ca1c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.44.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ef5753a17dc40819389dca0c39888001d5a7a1f09ac93bdedaef859e415c399c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.44.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bba9a20b235aa56a696ba39f9561ac5eaf385fc6ac7f92a7fc4b7eea1ebe3e45.packed",
"scales": "t_bba9a20b235aa56a696ba39f9561ac5eaf385fc6ac7f92a7fc4b7eea1ebe3e45.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.44.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_467467654f963b2b199cb6eebacf75a5ac8f6290bb8d740d4c84627f9ae143e8.packed",
"scales": "t_467467654f963b2b199cb6eebacf75a5ac8f6290bb8d740d4c84627f9ae143e8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.44.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_052b0e6da18c4625dac6c02eea00f9beaf71417f520c8b24a9463d1a2fd4b7c6.packed",
"scales": "t_052b0e6da18c4625dac6c02eea00f9beaf71417f520c8b24a9463d1a2fd4b7c6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.44.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9caea0e9ffca04599e6fd0e12d2cc0f549ff6856cfdf6493666ed4fc3824e26b.packed",
"scales": "t_9caea0e9ffca04599e6fd0e12d2cc0f549ff6856cfdf6493666ed4fc3824e26b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.44.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5fcadca18af8b6a6e4ebc93f85c7dc2a90e4f21adf48738b9d0e19f8d126bc7a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.45.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f9b61fedba6ee7fe3527beb0a9fa256ef0c1381dde84d3771c84aef5ec0a5252.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.45.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b68a6044981a3af32a453a47a145039375d42c407521b56a09c73b29dca08106.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.45.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c669aa1f50abb360f1f85ca5056a74d9f4a2a10f1fee45cc3f6dcbfc7d758205.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.45.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4965f1acb99a3423e4b4095a5875e96c68ae71dbc04797c41fb0ccb8956da636.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.45.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2db0995bacf65f4508ae546c8583e840ed64b7ba14d850ac907bb865a8eddc55.packed",
"scales": "t_2db0995bacf65f4508ae546c8583e840ed64b7ba14d850ac907bb865a8eddc55.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.45.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b1e4eb7a9ae247ed1b2993b1b758961aa76b6b2fe49a886fb8b8d5b01d981d7a.packed",
"scales": "t_b1e4eb7a9ae247ed1b2993b1b758961aa76b6b2fe49a886fb8b8d5b01d981d7a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.45.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_379606c6a2149a2a8d3c998ae8cc6954c29ca4a89d87e54e4e434f30980734db.packed",
"scales": "t_379606c6a2149a2a8d3c998ae8cc6954c29ca4a89d87e54e4e434f30980734db.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.45.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_da6622fb0575155d590d4edc37456c7ac43ab4fbb89f670b84a38fd5c74d46c6.packed",
"scales": "t_da6622fb0575155d590d4edc37456c7ac43ab4fbb89f670b84a38fd5c74d46c6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.45.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_034993577e1ecf1e45c45464316bac0632cb66cb0721fd20140371ffc3df64bc.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.45.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_66a112fa02a4c59342c7112471f4f0ca1f232456702d4221cf58659f9ab665d6.packed",
"scales": "t_66a112fa02a4c59342c7112471f4f0ca1f232456702d4221cf58659f9ab665d6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.45.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0821a9ae81019c9c34d6d3cb82ab41ea48e6bdf5bfde71d180b0a4c501c1935f.packed",
"scales": "t_0821a9ae81019c9c34d6d3cb82ab41ea48e6bdf5bfde71d180b0a4c501c1935f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.45.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_30bed0b7432af42854bb9954328432ef63900bb84e372539ef4196a62782468e.packed",
"scales": "t_30bed0b7432af42854bb9954328432ef63900bb84e372539ef4196a62782468e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.45.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c5a2b7d25c916a6f6cb1997fe80b3fc7ba3b311519d833afc253a2a6a75e2c4f.packed",
"scales": "t_c5a2b7d25c916a6f6cb1997fe80b3fc7ba3b311519d833afc253a2a6a75e2c4f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.45.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_698b42b1b38a61ac1e05a6e0a58f259bb25390e0689243c6b13a267667c8da2b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.46.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d6c7590ad5d71a005c4abf96f7b2722550a1e574214260240ed74c06c7e6f3d7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.46.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a3818ed1eac013032716c6dc85a1a5fdd253b96a3bc901849b3f4a3a7d53a49d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.46.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9592b804a76ae248ac5bd7b6c698dc5915748433ef6b52d3ca677cd3649c3513.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.46.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cd253497b122dfbbb48ffe934763034589dfceb3caa72c3719c3975703c08e99.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.46.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5556ae1fb2f9d9b791078b860a7d387af978140be986d7f97f07dda2a7aebe45.packed",
"scales": "t_5556ae1fb2f9d9b791078b860a7d387af978140be986d7f97f07dda2a7aebe45.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.46.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_57311618e8fde65ef7713876588a34a8e5780b3be735b3662482c73d8fd3e560.packed",
"scales": "t_57311618e8fde65ef7713876588a34a8e5780b3be735b3662482c73d8fd3e560.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.46.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3d062719cf14f8287b540e675bf9b39503fd382b8cdba279066698f95f493661.packed",
"scales": "t_3d062719cf14f8287b540e675bf9b39503fd382b8cdba279066698f95f493661.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.46.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_03725fe01849c7062b9d1164a8f77e30dd5365ee5f775594a125dce38528f826.packed",
"scales": "t_03725fe01849c7062b9d1164a8f77e30dd5365ee5f775594a125dce38528f826.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.46.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7f687acbc29aa93d09736f2a815083bdbd07fd0d211adce392880ec8efa71b10.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.46.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_517cd8083db5b9ff60d99213b6eb7352c33e3f4b128d7e3b5c95d0d510f20db7.packed",
"scales": "t_517cd8083db5b9ff60d99213b6eb7352c33e3f4b128d7e3b5c95d0d510f20db7.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.46.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d5adee056389e9adc208c4363841f58008644133e594d56e9b0abd47c7d24d7e.packed",
"scales": "t_d5adee056389e9adc208c4363841f58008644133e594d56e9b0abd47c7d24d7e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.46.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_82e5294263745ef278ea57e3dd6c8b917178cd0ac4f2e452ec953eb22357e59f.packed",
"scales": "t_82e5294263745ef278ea57e3dd6c8b917178cd0ac4f2e452ec953eb22357e59f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.46.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_84232b3b3f277e046c4131f1e44523a640a60d527c29de14e390bf407f2651a2.packed",
"scales": "t_84232b3b3f277e046c4131f1e44523a640a60d527c29de14e390bf407f2651a2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.46.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_780cd2b23b3d8ae231577dc8767d441014efd77b6422766ee5426a459867b7be.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.47.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9ec3f2e6a6cec873e6504362d12551ed4f2802ef4e7f02142ce8acfe820e1159.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.47.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_967a7f5af8815107906b4f7618a7eb20fa4bb494886d14bf9d59c69ade51eb1f.packed",
"scales": "t_967a7f5af8815107906b4f7618a7eb20fa4bb494886d14bf9d59c69ade51eb1f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.47.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e059f31ba71c391147f499691838cfa00b65115d0cfd97a62d2c03d93ed23ec3.packed",
"scales": "t_e059f31ba71c391147f499691838cfa00b65115d0cfd97a62d2c03d93ed23ec3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.47.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5fa5b782b58eddc3197236db89d5102039e4685b3372cf5b9c948100d2cc87f8.packed",
"scales": "t_5fa5b782b58eddc3197236db89d5102039e4685b3372cf5b9c948100d2cc87f8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.47.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9eecc1e315a17b80e3f11578119858f07b0d48d9ed5453d3090de322bae6cd5d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.47.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cc7ad7357323b0ca15a4f8fdc3898b09c82ed440c7bf02f71e16420579620410.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.47.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_adcf33b4ee94a4147ff9af8c9fc29a58196e413445ffe2a3b42cdff39d0c7958.packed",
"scales": "t_adcf33b4ee94a4147ff9af8c9fc29a58196e413445ffe2a3b42cdff39d0c7958.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.47.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b869f30a97ebcc795976be12a172d94e8f94cded85673cdcd2c4b77900b1111b.packed",
"scales": "t_b869f30a97ebcc795976be12a172d94e8f94cded85673cdcd2c4b77900b1111b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.47.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_733757fbda8ecc34995dc7bb8df27e8edb3a65050499992d36ccdf8e703dfaa9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.47.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fabae121e7805d8c995a93c0a48b26218ddd36acad78908ee88bbccd864379c9.packed",
"scales": "t_fabae121e7805d8c995a93c0a48b26218ddd36acad78908ee88bbccd864379c9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.47.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5fd38b96a41cf3d2432f2c087989270f0ad6cb5dee186165eb5b6583733d4647.packed",
"scales": "t_5fd38b96a41cf3d2432f2c087989270f0ad6cb5dee186165eb5b6583733d4647.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.48.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b6b33a5fe9d5f4ced43e61381211b487a3727c546dcbde385f50462e845377b4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.48.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7c5867719043e1029602946cf66b3e3bbdb4b74bf6da0d2951f82d6da3416635.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.48.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_55533c38337bd32d7dbe9992b7926027bc654f18023a288a5e417c07b70fc5d8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.48.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1fad852b0429781dabc03a0722aaa1c6120378b50ab68eea097b76a568b66ebd.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.48.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_09a1210ed39554d47e728018d424e4cf46327f3202605aad572f3907b326f467.packed",
"scales": "t_09a1210ed39554d47e728018d424e4cf46327f3202605aad572f3907b326f467.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.48.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f211e1b7a5d078537dccb81df2f0a331330706d700074c4e3e7b78ecce1f2b8b.packed",
"scales": "t_f211e1b7a5d078537dccb81df2f0a331330706d700074c4e3e7b78ecce1f2b8b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.48.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_30eb7c3e04cd4fd76c23973c812d2fd92bcb47ce08fecb814695459a9763fbd4.packed",
"scales": "t_30eb7c3e04cd4fd76c23973c812d2fd92bcb47ce08fecb814695459a9763fbd4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.48.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c6b9fc206a40487a93e0e5cfd343423d468c2935eb1afd94c48860cd4024430d.packed",
"scales": "t_c6b9fc206a40487a93e0e5cfd343423d468c2935eb1afd94c48860cd4024430d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.48.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ce5eddde212e1c6511bd45e9ec1eb4ed38610fed0ae838f0958b868a4cd2602b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.48.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ffcde0987ea84880e283b656f432a55443ca79f8fceb3801fca3826f67819282.packed",
"scales": "t_ffcde0987ea84880e283b656f432a55443ca79f8fceb3801fca3826f67819282.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.48.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0cb74f61cd7628a21a944cd31006742657971aa44170704d0bcb5549774d348e.packed",
"scales": "t_0cb74f61cd7628a21a944cd31006742657971aa44170704d0bcb5549774d348e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.48.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cd245ecec9860c2d9999b36c3f8302f4ad155c87474ff0f08ab469cc76addbca.packed",
"scales": "t_cd245ecec9860c2d9999b36c3f8302f4ad155c87474ff0f08ab469cc76addbca.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.48.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e02e5998682969a12da493b17dd00d70367198b872f26d5d05ce72a39ce319e3.packed",
"scales": "t_e02e5998682969a12da493b17dd00d70367198b872f26d5d05ce72a39ce319e3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.48.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_fe8fbd7d031b66b0864ed665591e62b27e9c9dcfe9ca4c02643e9e6959d9d313.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.49.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4768db55935ea4e8e1e3041849e29ccc03056faa986b88ceadf9c92f0b3752f3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.49.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e1fa093679b47204af1ba708c138ffa992c4fdd74e8b8fda9148e1232141e5f0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.49.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_ca784d265bbcb9f87438b580beb2150364037864848cd57ccf9c7b2e470c2be8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.49.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_4d668ae0286a3d87dd1919c08534e4f0021e9fa0644d44151c7e50588bd6e77f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.49.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ed2f16479f373e2362bfc28783e1299b63c06d7373b3972ed41faf72c8fc5f9c.packed",
"scales": "t_ed2f16479f373e2362bfc28783e1299b63c06d7373b3972ed41faf72c8fc5f9c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.49.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_893d76f036ac8a336062d1fbf0b13bd76eafc3855c3d78c721ea13de0522867f.packed",
"scales": "t_893d76f036ac8a336062d1fbf0b13bd76eafc3855c3d78c721ea13de0522867f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.49.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_21776cd1afca1dbb68deebdf53c231f8bec73a6a5e55cbf9f3c70e505043f2e4.packed",
"scales": "t_21776cd1afca1dbb68deebdf53c231f8bec73a6a5e55cbf9f3c70e505043f2e4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.49.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a2ddbbae8de46c2932bdd80c06d5f01edbce6f3923ab351fcd4bf7bb648406a0.packed",
"scales": "t_a2ddbbae8de46c2932bdd80c06d5f01edbce6f3923ab351fcd4bf7bb648406a0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.49.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f65d291d5e96224d3486cd31d855449381f688172ab892c646167f59c08f3a99.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.49.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_836f848361daa66828391b6167cb0fa3c1af139a8e9beccb7d30550aa22a8a40.packed",
"scales": "t_836f848361daa66828391b6167cb0fa3c1af139a8e9beccb7d30550aa22a8a40.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.49.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_468b55d42d62707a696ec1881c7fe53216a0534184ab5e0ad794adb35b3085b5.packed",
"scales": "t_468b55d42d62707a696ec1881c7fe53216a0534184ab5e0ad794adb35b3085b5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.49.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1317cee46c5dc698cb50a4b0217f8b5e993e8b4f1ab779a1f85ca151bde5df42.packed",
"scales": "t_1317cee46c5dc698cb50a4b0217f8b5e993e8b4f1ab779a1f85ca151bde5df42.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.49.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_40893074313d11ca68c866fdb6d1adc8d245603db29e777d330c30042baffb90.packed",
"scales": "t_40893074313d11ca68c866fdb6d1adc8d245603db29e777d330c30042baffb90.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.49.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cc1aa4a8fe3914625eeddbc8cba343cbb9fbc07464214a2d1d740d5009408774.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.5.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3a47dc47e1dd04e658986311f44f4256dc388614f0a26c4bdf6ed4ba9595f183.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.5.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_aba8e84305e66d2214282de7ac551bddffd2258ced59a0f0f06390a910e940f0.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.5.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3e755b3c7378187e32de009771cece87f1fafa31018c73028f7c5cae2249cbc8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.5.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_0ef365a854f9bd50bacef0d7c7de7f855a83a81db2766510581152a619a7f295.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.5.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b5fc4782724d7ffaab714ad5a17b5195396bc4a88a423bf19c40cc2c0e22dbf9.packed",
"scales": "t_b5fc4782724d7ffaab714ad5a17b5195396bc4a88a423bf19c40cc2c0e22dbf9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.5.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bb19bb24d8071cdb9fd83116ade86e070926d8f916a40d6a9a8c8433947b0251.packed",
"scales": "t_bb19bb24d8071cdb9fd83116ade86e070926d8f916a40d6a9a8c8433947b0251.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.5.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e995cb3c3216dc83e939c13af840c7dbafd233fb9f9103c0ab0dfe9c63594eda.packed",
"scales": "t_e995cb3c3216dc83e939c13af840c7dbafd233fb9f9103c0ab0dfe9c63594eda.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.5.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_24a00519964af8c400d5f7764528d51621612abecb9b0c5b57d043c459df3f1c.packed",
"scales": "t_24a00519964af8c400d5f7764528d51621612abecb9b0c5b57d043c459df3f1c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.5.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7ec5966299b0404df43c994cf77936bd7adf3bb0b6894d1fcfea09d21d5ec56b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.5.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7f953b3ee3042ddc159c3eda9f211ffe5e5a58ea6fac8e57d024b8f8930a1cf4.packed",
"scales": "t_7f953b3ee3042ddc159c3eda9f211ffe5e5a58ea6fac8e57d024b8f8930a1cf4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.5.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a8fa60c9ddcb31801b27590ecb8dc8b439780149ecf48a0225b86e8791d23659.packed",
"scales": "t_a8fa60c9ddcb31801b27590ecb8dc8b439780149ecf48a0225b86e8791d23659.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.5.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_449702c70a0f3b367747e2db086ad2053a30276f4e8486f894e29fe2457b4abe.packed",
"scales": "t_449702c70a0f3b367747e2db086ad2053a30276f4e8486f894e29fe2457b4abe.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.5.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c74a33289d2f4e3bac30805ca0c7ca019d9a8818efc1f48d4e8e458eb7277a05.packed",
"scales": "t_c74a33289d2f4e3bac30805ca0c7ca019d9a8818efc1f48d4e8e458eb7277a05.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.5.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b17427c9f08551fd16f3395a0aeea984f813deccff334bbfaf65ac44bbbb08dd.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.50.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_fef7687b169ca7d635f2506a2b94a8273399b60cbbd0bf80df8087e236dcf520.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.50.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9cdc7188bf491825dcc389dc23adf43c9a951ce8d359cf3dcd5c0726fc15d567.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.50.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5e0c755f45f5a47047719b4310ad7997fc6fc2b5bdb0da4ee6392dcce143b7ec.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.50.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_32c838c91a1a2dfcb0c2fe7493e2aa8b1a683d7955a9f9cb1622eb44d5127b44.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.50.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ca5e551a97fcab63b9692844226b8de1d8e34dbe373eb3f7b5a050ab1dcb448d.packed",
"scales": "t_ca5e551a97fcab63b9692844226b8de1d8e34dbe373eb3f7b5a050ab1dcb448d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.50.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f8dccf40368891a6127f4aef67f0922a971ba21849e6b0a6540af9ee3a60e5f8.packed",
"scales": "t_f8dccf40368891a6127f4aef67f0922a971ba21849e6b0a6540af9ee3a60e5f8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.50.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d5fd80322e31938529970fd1632c7dfa57738413680fc5f8bb46fbaa9218ef0c.packed",
"scales": "t_d5fd80322e31938529970fd1632c7dfa57738413680fc5f8bb46fbaa9218ef0c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.50.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_196b29f8eaa73684b150691c409eeac446fd1a650afc0993c6dc350424261751.packed",
"scales": "t_196b29f8eaa73684b150691c409eeac446fd1a650afc0993c6dc350424261751.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.50.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_90ffbc4e24dd16fbca65242db64fc6daed15673a7b4508c01eb3b802f4f42460.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.50.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_35d428b25e75235c8005058a26b82eeecf63cbb20a4a754854052c3360eef75d.packed",
"scales": "t_35d428b25e75235c8005058a26b82eeecf63cbb20a4a754854052c3360eef75d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.50.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6f078c432ddb1bf45d404caf558cb278c166ebb3feacb93353feb9fe1e04e8ae.packed",
"scales": "t_6f078c432ddb1bf45d404caf558cb278c166ebb3feacb93353feb9fe1e04e8ae.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.50.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b736dc74c2281c9517157b6095a071eed34fdb260a4408ffc1499f515d6ce47a.packed",
"scales": "t_b736dc74c2281c9517157b6095a071eed34fdb260a4408ffc1499f515d6ce47a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.50.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e04a7983e7f97a740beb2b0d184b24fc7ba55aba33be46a68ebe34c6273a7d5b.packed",
"scales": "t_e04a7983e7f97a740beb2b0d184b24fc7ba55aba33be46a68ebe34c6273a7d5b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.50.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_89e36053be8fb58efe846c6b942d9629fa86cfe0e0b0b69c6246c71403b64067.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.51.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_8e57cc4d7e7d3f9c91ffb1f5ed72000b1b45233b8498eafac51d98d2673f15ee.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.51.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d03ba72e97cb475ba24611dc4d494b13c9ea9124187f856e33eb0c41080724e9.packed",
"scales": "t_d03ba72e97cb475ba24611dc4d494b13c9ea9124187f856e33eb0c41080724e9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.51.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_50e67d147f1e211c70661d3371609463812cb9c5f5164edc463dbba19f138414.packed",
"scales": "t_50e67d147f1e211c70661d3371609463812cb9c5f5164edc463dbba19f138414.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.51.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1911d239d590d3c81665462c64999a88e2334fb02de2614fad03317d56aeb30c.packed",
"scales": "t_1911d239d590d3c81665462c64999a88e2334fb02de2614fad03317d56aeb30c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.51.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cfb0c9995207e1daa518d88a0cf267ad2b3ff012903992042399f1aeaaaad30b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.51.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9dd38f0bb1c2044293e11712229f9816b324bb29d80c8f549bb208b4a1376eef.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.51.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f966bf36d39fbe9c21ab6b22553623a3c416b8f57a74f16f30fdeecfdd696afe.packed",
"scales": "t_f966bf36d39fbe9c21ab6b22553623a3c416b8f57a74f16f30fdeecfdd696afe.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.51.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a9adc25b61f999d558fe1b5398dbd2697b2bf9bcc6376c3321bf9a585bf07f7f.packed",
"scales": "t_a9adc25b61f999d558fe1b5398dbd2697b2bf9bcc6376c3321bf9a585bf07f7f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.51.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_20ea39879b7fa4c443739d4d740c3baa12fbbb631ed54b2251a29d4d84d5ccb8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.51.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_23118e4d5ba08ce7ca68ea8b783595287354f339306eda3361ec3f3eee58f2c1.packed",
"scales": "t_23118e4d5ba08ce7ca68ea8b783595287354f339306eda3361ec3f3eee58f2c1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.51.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b62326ad0cd96e63f7a699dff75b15cbfad6aff0e3ce07eb673b8c155f36fd0b.packed",
"scales": "t_b62326ad0cd96e63f7a699dff75b15cbfad6aff0e3ce07eb673b8c155f36fd0b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.52.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_210e5c951bc9afb3f33be0f246c8b590305e059affe2e38424e0183df170fb0b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.52.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5c607086f91b35bb8ed0d9e1e672ccae587e9ed71acc9b055f46bc6ad77f3fbd.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.52.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_2440007b8da8b9545d7c73feaa560a1667adc5f78f8fe8daa14bcd9d9fff9d71.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.52.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a24c8b6b62cb9cde6cd8a881304b165e7e4f9e2a71c088c56cf7ea58d7e033f2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.52.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_96195ef6953f088c7ce5d9150729d9682d99d6e003fd325f4dec38ed8992d6d9.packed",
"scales": "t_96195ef6953f088c7ce5d9150729d9682d99d6e003fd325f4dec38ed8992d6d9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.52.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5fdde3a4d4efd936458d48af51d8e9cad58fafd24a3fdfae38f32feeadb7e558.packed",
"scales": "t_5fdde3a4d4efd936458d48af51d8e9cad58fafd24a3fdfae38f32feeadb7e558.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.52.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_505138952dc4d9c587e463127505cb7c194ce5aaac243916834f37bc7d5024b4.packed",
"scales": "t_505138952dc4d9c587e463127505cb7c194ce5aaac243916834f37bc7d5024b4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.52.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9b237b640addfbab7c3837407e89073fd8f4d9afbf9d1f033c58a47ec089c692.packed",
"scales": "t_9b237b640addfbab7c3837407e89073fd8f4d9afbf9d1f033c58a47ec089c692.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.52.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_091c56d0e83c78b3ce179ce22281daa4b04521d6ce369dc46bedf6eb722f589a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.52.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0a332c37f4386e68550ac1abb38c11b1150f0655e7f400d63cffc45d3c4ae315.packed",
"scales": "t_0a332c37f4386e68550ac1abb38c11b1150f0655e7f400d63cffc45d3c4ae315.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.52.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8bba312c9bb86fc3cb96bcf5171ee9dd845041c7fe7123c02d52f337af17e46a.packed",
"scales": "t_8bba312c9bb86fc3cb96bcf5171ee9dd845041c7fe7123c02d52f337af17e46a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.52.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_2bb0ca9ad2ca927cdec48745dd55217d156602c632b663cbb79a00be75f687be.packed",
"scales": "t_2bb0ca9ad2ca927cdec48745dd55217d156602c632b663cbb79a00be75f687be.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.52.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_725b877400b2baa31772c606ee47d60ccbe88e01e65347b0491f277d13e6be09.packed",
"scales": "t_725b877400b2baa31772c606ee47d60ccbe88e01e65347b0491f277d13e6be09.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.52.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b08fa8fb67ab86d6bff51a32215cda6deba23a86c6fd9ab99950b0f79942a8ed.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.53.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_58ed08550fbe4e122039d26dc734a09c31ae79120b794fdb5728edd75d30b2a6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.53.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b861085df28c8810d229178bbcbf1f3a85dea6eb493465f1c450d3388e05cd4e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.53.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_88ed0f6f27feb1a93a5d96491b7874ceb61978dbfaaf23ba58a8b461f0e769d6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.53.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1df5049a69d6dc6551e97589991f23555cc80d0f64ef4003c7a10efa71c9a49e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.53.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_cd886b724a112cb8e16c238e9e1318b0e4c7528ec2e3a05890715c4210195334.packed",
"scales": "t_cd886b724a112cb8e16c238e9e1318b0e4c7528ec2e3a05890715c4210195334.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.53.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_10ec449924c0f4f67dc94d347b082330493b7afd21cf4f3f9762a5287565d5e6.packed",
"scales": "t_10ec449924c0f4f67dc94d347b082330493b7afd21cf4f3f9762a5287565d5e6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.53.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_8734c12fd674bcb8fdc21a4613a6f8b666a03e2a1c854ee303ccb181443e34d9.packed",
"scales": "t_8734c12fd674bcb8fdc21a4613a6f8b666a03e2a1c854ee303ccb181443e34d9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.53.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9515391d8929d151b981e9961964c5cee3485e24c24c9a7ffcec44cef0f7bf9a.packed",
"scales": "t_9515391d8929d151b981e9961964c5cee3485e24c24c9a7ffcec44cef0f7bf9a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.53.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e9bddef513984e4f3ad3beb39207b6bb0bd263aabf2534f456d2e4183953f0a5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.53.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_75ea3036af30b00c17b12bdbde28ce97081d34caf70024ef0b041d748eb35dd6.packed",
"scales": "t_75ea3036af30b00c17b12bdbde28ce97081d34caf70024ef0b041d748eb35dd6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.53.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d40aca84d3581f0df0ae2b48dfab7cf95f79e1ab08e71bb2ea7359984b990950.packed",
"scales": "t_d40aca84d3581f0df0ae2b48dfab7cf95f79e1ab08e71bb2ea7359984b990950.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.53.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_62e2710bb1b1eb8a0f942733a4d8fbfcff925d7f005bd953bf7a9e7377255bf8.packed",
"scales": "t_62e2710bb1b1eb8a0f942733a4d8fbfcff925d7f005bd953bf7a9e7377255bf8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.53.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_46e42a119d7532454f78479a690652af72813ee26624590b6306d6f5ab0c4d39.packed",
"scales": "t_46e42a119d7532454f78479a690652af72813ee26624590b6306d6f5ab0c4d39.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.53.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_463b011eb5c7fe56217f36889edcbdc28b0cb4c2405beea5c5833130aaabc121.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.54.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f02562fd09f17f0e40c5d0a4298ad8c6b071006539ef3c81459aa621ea7fb7da.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.54.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_354064aa1cd969b79dc232e64ec522c6cef4ac65470e455dc69d474cad5a1781.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.54.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_76bc09c45d05d4b03d62dde4bd0194812d0e96e16da9246aeb21e2c908e3e003.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.54.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_44972d236af69bdd048e870f7d06623f88f65f9c9ab9989bed2ae0069689e99c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.54.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_040a254eda58d8e3bba6eaceb75074d77b90f7d30a03d9d3248028867f045eac.packed",
"scales": "t_040a254eda58d8e3bba6eaceb75074d77b90f7d30a03d9d3248028867f045eac.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.54.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_759ba030c40bdca08ff80e2b1d73eee5e11849e100b2d64299e4c6326e3d8eae.packed",
"scales": "t_759ba030c40bdca08ff80e2b1d73eee5e11849e100b2d64299e4c6326e3d8eae.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.54.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5770d86c8f6887f1159f61e49c9b776ae99f2e887392cfabb0a15ec23ced0c15.packed",
"scales": "t_5770d86c8f6887f1159f61e49c9b776ae99f2e887392cfabb0a15ec23ced0c15.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.54.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_0b990261540a618534c375b69643b65e4e0ca34eacc548d4ef832c2c03d8e406.packed",
"scales": "t_0b990261540a618534c375b69643b65e4e0ca34eacc548d4ef832c2c03d8e406.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.54.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6d6853cbdba8c393b07de576898468cb918109cbf383114e68439f729d782880.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.54.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f8f1d0f9e821ced5469ac2ed23c83995f35145b8ec6fb52c183e683b62c3a07a.packed",
"scales": "t_f8f1d0f9e821ced5469ac2ed23c83995f35145b8ec6fb52c183e683b62c3a07a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.54.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_be756833f211d4d334280d5884deec75421bdbd2c20764377ff0996ba5f4a4d4.packed",
"scales": "t_be756833f211d4d334280d5884deec75421bdbd2c20764377ff0996ba5f4a4d4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.54.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_15b60d6e3eb7ebc019434b8c85df2d5f531c227069bebb091c362754be6302b2.packed",
"scales": "t_15b60d6e3eb7ebc019434b8c85df2d5f531c227069bebb091c362754be6302b2.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.54.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_44e476cbf0f5f7f478bf630cc41d456059be41cebfd648f5d1b0ac47664ed8b1.packed",
"scales": "t_44e476cbf0f5f7f478bf630cc41d456059be41cebfd648f5d1b0ac47664ed8b1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.54.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_603481cca683a063c417ec99be160d2baa5fa9d68c6c2cd21e5a4979adb6be13.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.55.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_a7b5eb595d9c7175af71e968258627ca82e1dfadee77e0ea321c780882623150.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.55.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_786ee7bc30d52030a717256bd0ba1ebaa5cff1765f7ba48e11bee0d7d10e6d25.packed",
"scales": "t_786ee7bc30d52030a717256bd0ba1ebaa5cff1765f7ba48e11bee0d7d10e6d25.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.55.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e7ba1d56d70a52ca2c997d7ca42f3fedd5303068eaa185769774b9be61814b38.packed",
"scales": "t_e7ba1d56d70a52ca2c997d7ca42f3fedd5303068eaa185769774b9be61814b38.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.55.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_705c0549d6bc99aeafc1c01a35945ba5ec87dfe02ad45cd4912bf4c9356f1088.packed",
"scales": "t_705c0549d6bc99aeafc1c01a35945ba5ec87dfe02ad45cd4912bf4c9356f1088.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.55.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e999bb074b8f8cb018a464832ff529f7bcf60ecbe6df1114572096b62d5d9d55.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.55.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_c7feb35e78a90719fa6d0eef2f17d898c221071d1f50a7629ac81ca5874321c2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.55.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4ef3199da34f54a6cc0cf0a1a21c9ad605864350578e87a374a5796f3c9b1ebe.packed",
"scales": "t_4ef3199da34f54a6cc0cf0a1a21c9ad605864350578e87a374a5796f3c9b1ebe.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.55.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c106c6f3514a1942e55cb15b7d810d5a87571d0f8245f966f6dbd19e8fb449ce.packed",
"scales": "t_c106c6f3514a1942e55cb15b7d810d5a87571d0f8245f966f6dbd19e8fb449ce.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.55.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_904daec8dcce84cac17fc5d31be30aeacdfb8c5866600dcaa6b620104c0217c6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.55.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_aaf2ef7a28b411b54e2621b2595e665a6ec658c4056024a39ba24df5b46b4040.packed",
"scales": "t_aaf2ef7a28b411b54e2621b2595e665a6ec658c4056024a39ba24df5b46b4040.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.55.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_746c5e267ba74a0316edfcdc2264f63aeaf16e0359309c4b93856a4d55cfaf91.packed",
"scales": "t_746c5e267ba74a0316edfcdc2264f63aeaf16e0359309c4b93856a4d55cfaf91.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.56.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_d41eede7469685aa49cc3dd30cbed8ca8627fca084e193f1f47a2dd292a6365c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.56.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5c7a10e5477ddedfd1c2811aa39c7e8d8a51db7e4e6a15de2fcba192d5ef7383.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.56.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_800e30d264b527b8d424958569cc2636e74affd8d1beb88c6b6cd7592371e9fa.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.56.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_edcc6b9c55c72091791576c4ec0651e5c14c1463f9ab61915c7ca87305c4fb7c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.56.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c0257dc7abd59d3d005774e0317cf0ceade44be6598863e404740664d843982e.packed",
"scales": "t_c0257dc7abd59d3d005774e0317cf0ceade44be6598863e404740664d843982e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.56.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5fdcd62344a937c9fc00d08c2aa4f49e693b3df418c91c2be553410d787135d1.packed",
"scales": "t_5fdcd62344a937c9fc00d08c2aa4f49e693b3df418c91c2be553410d787135d1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.56.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ec99dcac7f83ced708081e374b6518842ac884dd40a6acef447ceaf24db88299.packed",
"scales": "t_ec99dcac7f83ced708081e374b6518842ac884dd40a6acef447ceaf24db88299.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.56.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_17879a451d18d8555b993aeffddad6e32c816be7d58f779df1d24a561fcf6c7b.packed",
"scales": "t_17879a451d18d8555b993aeffddad6e32c816be7d58f779df1d24a561fcf6c7b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.56.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cb6c43873c1f69b579d43e1a475cf13a6b99b95b2d4c195c6c68cd80c2e2b2a5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.56.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b70f567ef1db836c53942a94560d765dfb31673c446064d67907a8cb990a1f6b.packed",
"scales": "t_b70f567ef1db836c53942a94560d765dfb31673c446064d67907a8cb990a1f6b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.56.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ad33432887d90b4271f01f783b8782221e2f983cf71b44a2274fd4030aaa5a0d.packed",
"scales": "t_ad33432887d90b4271f01f783b8782221e2f983cf71b44a2274fd4030aaa5a0d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.56.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d2ce2ee4b23209492d13c3c86c070f3400e29f18e1d5b73c9c6fc79d4994c7b0.packed",
"scales": "t_d2ce2ee4b23209492d13c3c86c070f3400e29f18e1d5b73c9c6fc79d4994c7b0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.56.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4becc1ed1bddc0604adc83e6cdb879209cf1cc99a2b58e9d2ecb48017a11d2b4.packed",
"scales": "t_4becc1ed1bddc0604adc83e6cdb879209cf1cc99a2b58e9d2ecb48017a11d2b4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.56.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e6facf2684d44d8647ae23184819175db8b78f970552eedd067d9563a68a1a74.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.57.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_766a48b0faf44ae12a6955531ab70768a165694d6c945750e834f7144c6f9d01.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.57.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_cbceb8ce77b8a7f4b36f3428cffeda0bba3a4ac66f843e0b4f512fb8bd4efd6e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.57.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_880c2fca7e9754760a675814355fb9751038188afc1ea5685f13f004a765d926.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.57.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1999333f69ebd0d148753ef4bc1a2ffbd82ddb834173c7e35afb2a17c7190784.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.57.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_75e93bc294b5b9c9bff4ab978c37a8e275a01e9b344c16723d5fe1a06a74a688.packed",
"scales": "t_75e93bc294b5b9c9bff4ab978c37a8e275a01e9b344c16723d5fe1a06a74a688.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.57.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_858a53b108b29041379f43ef7f02fd8178f9550308b73db6289735c8a6225306.packed",
"scales": "t_858a53b108b29041379f43ef7f02fd8178f9550308b73db6289735c8a6225306.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.57.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_42942d345d79411a8985d2caf3052649f6e845aa40ab95f0765abac7ffc6b743.packed",
"scales": "t_42942d345d79411a8985d2caf3052649f6e845aa40ab95f0765abac7ffc6b743.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.57.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4ed03173eb2823c053363740053bc27937fbd1463f5134b3e0f903397411ec37.packed",
"scales": "t_4ed03173eb2823c053363740053bc27937fbd1463f5134b3e0f903397411ec37.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.57.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_88f5905d694e9229d3e5bdf9600c985e8aa75d1f0fd777e6c54edeef1fa42db5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.57.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7cd0e399994185cd5f65d6bb5b9002728b1c45719b74a62ae3e5e892ae18781f.packed",
"scales": "t_7cd0e399994185cd5f65d6bb5b9002728b1c45719b74a62ae3e5e892ae18781f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.57.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f7607148ce2cb35abe79620368137a45095e063e1a8dc80864599f95202fafde.packed",
"scales": "t_f7607148ce2cb35abe79620368137a45095e063e1a8dc80864599f95202fafde.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.57.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b2913b3d8ca29434add0b78fa6c6287fc5d6f4da65a7854d9e40c67362675777.packed",
"scales": "t_b2913b3d8ca29434add0b78fa6c6287fc5d6f4da65a7854d9e40c67362675777.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.57.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_49554ae69ce0e5dec46fc991bda652094c0d059febd44f13dc825ca905cac9e3.packed",
"scales": "t_49554ae69ce0e5dec46fc991bda652094c0d059febd44f13dc825ca905cac9e3.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.57.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_07aab9e5fb302c650c798663985740aaec2aa7bd6efad68ee6d8a002956d5791.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.58.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6be15064b1c0f94e5666d6230430a885e422a40323b1f87236cbaadf8b97a407.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.58.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_154d5c53c32cb3f8c0e183560790d8586ca311045a400310032e2d9a02b8d43e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.58.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5db087a41441f44ce2ac267a79bbbf653a8246f2148d58658a4ac3d1da3f337d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.58.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_83f7bcee6fd99ce5aabcf3246bbfbebc77f7f441ea7961b567eda4bb18f90b41.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.58.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_823ee43f8ed5774551d657da097d365ca210451592c0574ecd3dedc9529b6c3d.packed",
"scales": "t_823ee43f8ed5774551d657da097d365ca210451592c0574ecd3dedc9529b6c3d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.58.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4a69bf6ee2703c9adf7dfe731fb759c31988c5622298cc5210f2008b87b3444f.packed",
"scales": "t_4a69bf6ee2703c9adf7dfe731fb759c31988c5622298cc5210f2008b87b3444f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.58.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_778a4ce74399da2b8ee8a2bddc7e240f7bf58cc1999405dd2d502fd8c9aad712.packed",
"scales": "t_778a4ce74399da2b8ee8a2bddc7e240f7bf58cc1999405dd2d502fd8c9aad712.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.58.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ab5924331734a951a30de18868533daa85895d625c4442413d8ee1c9d92556ba.packed",
"scales": "t_ab5924331734a951a30de18868533daa85895d625c4442413d8ee1c9d92556ba.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.58.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1041e3cab315e34dafb4d6bf54510e9e71ab8e42243936cd54b5764c0c6efc75.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.58.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_5b6014a3247222d8f34e282e7fb1bf0e7e3769a26dad9aae8bfa7b0edbf80b6d.packed",
"scales": "t_5b6014a3247222d8f34e282e7fb1bf0e7e3769a26dad9aae8bfa7b0edbf80b6d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.58.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_35e66d89040bafedc32e8e72468eb8581fd2498c709f1b99007fec6590ec24d6.packed",
"scales": "t_35e66d89040bafedc32e8e72468eb8581fd2498c709f1b99007fec6590ec24d6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.58.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b29cbc28dee152a0bb02066e438ecee0064c4ced48049b2e3bf64725c8be5f28.packed",
"scales": "t_b29cbc28dee152a0bb02066e438ecee0064c4ced48049b2e3bf64725c8be5f28.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.58.mlp.up_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_ab7d53a287cad3f02aefdc731f068009c3099cfc93202b9cc06ae6fb96409609.packed",
"scales": "t_ab7d53a287cad3f02aefdc731f068009c3099cfc93202b9cc06ae6fb96409609.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.58.post_attention_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_b295da2747db258f4d31c40088db45994cb6328b74c903b8b7beb8e5d8a5983c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.59.input_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_6b653d3afa1c35acf8b83380e78b11d6157b96f6b828e01c3b11cdad8204a143.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.59.mlp.down_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_e8e57f0231a2efd0a85aebed9c6fabf9238f71d1afa72aa1f954214c9a9add8e.packed",
"scales": "t_e8e57f0231a2efd0a85aebed9c6fabf9238f71d1afa72aa1f954214c9a9add8e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.59.mlp.gate_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_8218ec9322fa2c7d8b9ef411f0db1f1ef40fc8c3988abf8c5646ebc1140b83c4.packed",
"scales": "t_8218ec9322fa2c7d8b9ef411f0db1f1ef40fc8c3988abf8c5646ebc1140b83c4.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.59.mlp.up_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_510714b466f9cb159413749d0731709e2e13e02717dbf2344888e0e4c825c188.packed",
"scales": "t_510714b466f9cb159413749d0731709e2e13e02717dbf2344888e0e4c825c188.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.59.post_attention_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_2e3c8b6520e9cff764297893a57fcc7e4e3c21ed3400e99b8c86c04f85ebb707.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.59.self_attn.k_norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_6d93537ef69e6a641053d13a0886ad5d64b69ce84eaca8d3789d5cc1e9798a28.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.59.self_attn.k_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_567d15b9a468be76ccbae4b64a7cf768201ea03c879261539a7bb8084d5c1f23.packed",
"scales": "t_567d15b9a468be76ccbae4b64a7cf768201ea03c879261539a7bb8084d5c1f23.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.59.self_attn.o_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_b459e3e599bbc5c236f9021a97868b35c20edb4971a399238f06ec7334663e5e.packed",
"scales": "t_b459e3e599bbc5c236f9021a97868b35c20edb4971a399238f06ec7334663e5e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.59.self_attn.q_norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_e987ade76f459502230ae9d56ca01dfb822f00cb19cc4bb0d4481969f9181cb1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.59.self_attn.q_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_365307ddf25ef6f658669ea01a2573585889d307dada07cff623c3674b151f71.packed",
"scales": "t_365307ddf25ef6f658669ea01a2573585889d307dada07cff623c3674b151f71.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.59.self_attn.v_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_c81ee23847c19ef1c9853924396abf9a44f918c8d2065eeb7d2b7822f8dd87a9.packed",
"scales": "t_c81ee23847c19ef1c9853924396abf9a44f918c8d2065eeb7d2b7822f8dd87a9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.6.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_9b703c5d7c2082825d541616d667be4d125acf82c4b01a71a33d8968bc2ffbd2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.6.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_5dc3a0bc72727672339d29b20bf9456d5c16b4bc764921cc428305f0c40b5198.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.6.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3c5b8de1c6bc5dd93db04cc87453cd2202e7736f3d70c5aa3a811e8e874911c5.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.6.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_eeb191584d2df9c459c7fa5aea6c4809c157be0d4d9ba499fcf8dcc203a7ad42.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.6.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_4e7bd11c99aa44e4afa6559fb27b19247bc44c425166b7f12c4fcd64283e8b3b.packed",
"scales": "t_4e7bd11c99aa44e4afa6559fb27b19247bc44c425166b7f12c4fcd64283e8b3b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.6.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_e18cd819922034f66468dcfd85f0373b5146a086823a67c2f7e8effc54dab3d0.packed",
"scales": "t_e18cd819922034f66468dcfd85f0373b5146a086823a67c2f7e8effc54dab3d0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.6.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_6a0f3b5792d0ab0ab464af04da8feb8d667e7feda049ab29e85a9e9b2dda1145.packed",
"scales": "t_6a0f3b5792d0ab0ab464af04da8feb8d667e7feda049ab29e85a9e9b2dda1145.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.6.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7a844e5da7e362b9dfee5b930b3cccb82a4bcadf2b11f4639a3e984a6cd43be8.packed",
"scales": "t_7a844e5da7e362b9dfee5b930b3cccb82a4bcadf2b11f4639a3e984a6cd43be8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.6.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_b8e3ca42f034f2288bb6f75efdf0ea3d1271d3374cf29ece9b94f7b82441e02e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.6.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_3fce78f70d098a5aaa063a68647cec05cd9eb93a1eb734f704c999911ed9797b.packed",
"scales": "t_3fce78f70d098a5aaa063a68647cec05cd9eb93a1eb734f704c999911ed9797b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.6.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a53a76f27ea149b1432ab71a610960b733670424f7bac18a71dc8f92b288e7be.packed",
"scales": "t_a53a76f27ea149b1432ab71a610960b733670424f7bac18a71dc8f92b288e7be.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.6.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_7315b60fb0f087fc41913a9a9e368f71ed2e601346f69752ee15b071178676db.packed",
"scales": "t_7315b60fb0f087fc41913a9a9e368f71ed2e601346f69752ee15b071178676db.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.6.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b5e110a8c271667a9eb869b3a23d795a7adbf53d6db4bf28c2ff0002555fb236.packed",
"scales": "t_b5e110a8c271667a9eb869b3a23d795a7adbf53d6db4bf28c2ff0002555fb236.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.6.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_83a35aead4011d0d8430fe60ce78182f8cae21466769505ba08fe0ff153e4b7c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.60.input_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_0db2359d8adb0c986430976b09378cc5746336e039391538560dc57ec948ebe1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.60.linear_attn.A_log": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_572e86066f7f8fb84738335403f0428fa08e73f8c16e7635e613734e979ad9ce.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.60.linear_attn.conv1d.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_9c4574d7e46593aa8f4e88d35e59fe3cf1d45ebc9d5329a3818c263161660af1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.60.linear_attn.dt_bias": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_18a2b4f814611acb792f22517db201fe0d9fc40e3ff45f743bebb54ce2b743b7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.60.linear_attn.in_proj_a.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_19e801e3fa61f40dd24bd231f1f111b37c5ec9607390f8f494e8cdbc1df23452.packed",
"scales": "t_19e801e3fa61f40dd24bd231f1f111b37c5ec9607390f8f494e8cdbc1df23452.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.60.linear_attn.in_proj_b.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_3dfb042a13bdad3677783e824ab3540364e8ea14c34dfb49a442d7546ac3495d.packed",
"scales": "t_3dfb042a13bdad3677783e824ab3540364e8ea14c34dfb49a442d7546ac3495d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.60.linear_attn.in_proj_qkv.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_193b56df87d1fa5182592129ca93648caef54084f46f317427058a521c0212c8.packed",
"scales": "t_193b56df87d1fa5182592129ca93648caef54084f46f317427058a521c0212c8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.60.linear_attn.in_proj_z.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_f1054e8b395315e094d8c0151d4ad6a04cf379e9053836fdf072e1164b87378b.packed",
"scales": "t_f1054e8b395315e094d8c0151d4ad6a04cf379e9053836fdf072e1164b87378b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.60.linear_attn.norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_35d67d44b41aef707f67fdb08133b9cc52aa76829d6938efab66406fecd689a9.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.60.linear_attn.out_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_63ddc656c1bd70cbc10e43a1e79b12f9653bfc48c3a4b8d68f8717d535f47342.packed",
"scales": "t_63ddc656c1bd70cbc10e43a1e79b12f9653bfc48c3a4b8d68f8717d535f47342.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.60.mlp.down_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_472ca946b7426cc88be9fb71e61571662ad0453f5b1eb33cf2a420a0143e1e4c.packed",
"scales": "t_472ca946b7426cc88be9fb71e61571662ad0453f5b1eb33cf2a420a0143e1e4c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.60.mlp.gate_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_f5a5e7012e9559e4237012ec44149bf91637248e252b11a242d3acfe8bb57aed.packed",
"scales": "t_f5a5e7012e9559e4237012ec44149bf91637248e252b11a242d3acfe8bb57aed.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.60.mlp.up_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_5419cbec9204f31876b2cb5aa73604c56073bfecfab6dcff6078e5fbc2f201e8.packed",
"scales": "t_5419cbec9204f31876b2cb5aa73604c56073bfecfab6dcff6078e5fbc2f201e8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.60.post_attention_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_a8aae52a1b5046387e59d093fd3c0fe4c505ae2bfefa7f17dd063354dafda989.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.61.input_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_18c1ae0f43792770e0d92eeeefff5e4fc93f32fe5043eb0b90caa54582d5adf1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.61.linear_attn.A_log": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_bb01d1485cceb4d401a3bea9c0eec9944c89c5106dea85395abc3340488796f7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.61.linear_attn.conv1d.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_b7ea7e8d76985998fac434e0f8afcf87e1e9e2333c0e6c5b67547364d2a4d93e.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.61.linear_attn.dt_bias": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_150923315ecc23890290a42d9e9196c4574d12f37a27673e9518c8e37eb6e488.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.61.linear_attn.in_proj_a.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_a08cf91d2d523de8d5253fc05c279832ed3a6de66ce62cd4176ebf5b528f1ba0.packed",
"scales": "t_a08cf91d2d523de8d5253fc05c279832ed3a6de66ce62cd4176ebf5b528f1ba0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.61.linear_attn.in_proj_b.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_fc6629067660a212139084f6f88724fc515614a2976cd3dd1652dce9adfec9fa.packed",
"scales": "t_fc6629067660a212139084f6f88724fc515614a2976cd3dd1652dce9adfec9fa.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.61.linear_attn.in_proj_qkv.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_b5474655950483375bb6cbd68e6826fcebf397435849da8e0cc87666bc2b30f5.packed",
"scales": "t_b5474655950483375bb6cbd68e6826fcebf397435849da8e0cc87666bc2b30f5.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.61.linear_attn.in_proj_z.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_d4145b3a23012c7803d7fecf41996236adeb1b5b1730198008e42ca71db080ac.packed",
"scales": "t_d4145b3a23012c7803d7fecf41996236adeb1b5b1730198008e42ca71db080ac.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.61.linear_attn.norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_2c14cf0dda16350b90c38a45f2aa9d2c4d0bb7f5ba6073594444758896d4095b.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.61.linear_attn.out_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_f80af76c0f24f415c9b79f355326109a64d5d22d7f61f61a60193999178d3987.packed",
"scales": "t_f80af76c0f24f415c9b79f355326109a64d5d22d7f61f61a60193999178d3987.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.61.mlp.down_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_17aa508faee17d2ebd467f607249d2e3a2e398e78bfff858c76734721d02743c.packed",
"scales": "t_17aa508faee17d2ebd467f607249d2e3a2e398e78bfff858c76734721d02743c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.61.mlp.gate_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_2c39673e2d579298534209957a85048df94158fbabd39b3f516393e30adf328e.packed",
"scales": "t_2c39673e2d579298534209957a85048df94158fbabd39b3f516393e30adf328e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.61.mlp.up_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_8d71a6c2cb316c813ae9d5ce5111054b0f061f849a6db8c8450109d1910adda6.packed",
"scales": "t_8d71a6c2cb316c813ae9d5ce5111054b0f061f849a6db8c8450109d1910adda6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.61.post_attention_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_38ac0e1fb55e94ea87d3a0f0cd21e228e2174fef530a6925ec1850e6c78253c7.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.62.input_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_35a84fd8ab1aa482e76b91aa3ba49d46b161c49448259fd0edc2e9382471fc49.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.62.linear_attn.A_log": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_fe1c715f90e53f4011ece1ba08b603c30f576c9a2cc2f55fddb811767d0da63a.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.62.linear_attn.conv1d.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_52905109f20980c47826e615469ee597adbb1f6ae7964574d88401982c6f4fa6.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.62.linear_attn.dt_bias": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_d60444ab66bd21d191bf44f110cf53c5e4b8c3aa0d9e7a9b0c64149bcaabc403.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.62.linear_attn.in_proj_a.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_d0d4206a175629795b9277dfb132e0c5fea37cd9f7c17122fe70328b8b6c86d6.packed",
"scales": "t_d0d4206a175629795b9277dfb132e0c5fea37cd9f7c17122fe70328b8b6c86d6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.62.linear_attn.in_proj_b.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_742f79e0efab1882154a4d0c57d610bcfa773f1229f2d2a028ab11f62f2d602d.packed",
"scales": "t_742f79e0efab1882154a4d0c57d610bcfa773f1229f2d2a028ab11f62f2d602d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.62.linear_attn.in_proj_qkv.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_07f896691b8d9600f9b28f2c90ccd73d094c0ca4468d42838caa0b8614e7d78c.packed",
"scales": "t_07f896691b8d9600f9b28f2c90ccd73d094c0ca4468d42838caa0b8614e7d78c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.62.linear_attn.in_proj_z.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_cf466a6b83bdf7a33c0f3a835e0bf185f99bfdcedcf57893dff190ea9f1010e1.packed",
"scales": "t_cf466a6b83bdf7a33c0f3a835e0bf185f99bfdcedcf57893dff190ea9f1010e1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.62.linear_attn.norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_cd18355584a0ff2e5cf58d80026453a76a0c341f43030d839d3f9b703cf4e857.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.62.linear_attn.out_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_120c3d5fa8c62d90726fefdb72382014651ee61d65a72c8c74772d8bfdb0333c.packed",
"scales": "t_120c3d5fa8c62d90726fefdb72382014651ee61d65a72c8c74772d8bfdb0333c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.62.mlp.down_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_1f75016f51765bb06fa6dac56f35041768ff340b6753183f1487fdfa8c9ac4c6.packed",
"scales": "t_1f75016f51765bb06fa6dac56f35041768ff340b6753183f1487fdfa8c9ac4c6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.62.mlp.gate_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_659558fe86ad678feefa066e62625f65750cba11013b462eb70d285261ee8c8b.packed",
"scales": "t_659558fe86ad678feefa066e62625f65750cba11013b462eb70d285261ee8c8b.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.62.mlp.up_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_077d7188d2ec061e5237cf0b5e91ab948f7ddf6a11b57b07e46b0f64f0b4b53a.packed",
"scales": "t_077d7188d2ec061e5237cf0b5e91ab948f7ddf6a11b57b07e46b0f64f0b4b53a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.62.post_attention_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_f36cef602997d537e68b8acbcd8efa7a5ce1af0e17ccdef67de87997d7598ef3.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.63.input_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_d05f702c8476814b6211f7f3e9bdccdb862554b03f2aedc3f359b29ac3d27ed8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.63.mlp.down_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_09bd97a13bce4de37d8e8d8b8932f0e2aa4155bbd251475ae6860518380c0f91.packed",
"scales": "t_09bd97a13bce4de37d8e8d8b8932f0e2aa4155bbd251475ae6860518380c0f91.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.63.mlp.gate_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_98f376101380e12b129d9cbd00392361a971d35b57053b1a7c067fb768040a6a.packed",
"scales": "t_98f376101380e12b129d9cbd00392361a971d35b57053b1a7c067fb768040a6a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.63.mlp.up_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_48a8e73ef1ca29dcdaeaa3da061ddfba7cd210bf41232251f5b7f90111626341.packed",
"scales": "t_48a8e73ef1ca29dcdaeaa3da061ddfba7cd210bf41232251f5b7f90111626341.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.63.post_attention_layernorm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_660dd3b7672e1c036ff41e1ebd18c64562afc9184f5b9dbcdb18dead3baeadca.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.63.self_attn.k_norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_a561a24c308fa1a90259b119a7a0ff34daf585d3084e0588e101cf80bff9d474.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.63.self_attn.k_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_bc590ee97df5eefe4e84add023bc9e40971bb9dc4b01a25b7d7f6898d5becaac.packed",
"scales": "t_bc590ee97df5eefe4e84add023bc9e40971bb9dc4b01a25b7d7f6898d5becaac.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.63.self_attn.o_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_19a8e32dc54603bb03f83851948094e56b54877a33632ee1b44e6ef585c4b16a.packed",
"scales": "t_19a8e32dc54603bb03f83851948094e56b54877a33632ee1b44e6ef585c4b16a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.63.self_attn.q_norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_718c776afc9309b981c4cb96cd0a8ae07dc08114b2009b74a48bbe4225104f72.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.63.self_attn.q_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_d76d9a7fc8494cf7e8d040569828171c073e05234f83cbc5d5ea063aaadb4b7e.packed",
"scales": "t_d76d9a7fc8494cf7e8d040569828171c073e05234f83cbc5d5ea063aaadb4b7e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.63.self_attn.v_proj.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"packed": "t_7fc32a7ce254c6c349affe4b844068ac0e88383c46254d2c78c2422dcc7cdba9.packed",
"scales": "t_7fc32a7ce254c6c349affe4b844068ac0e88383c46254d2c78c2422dcc7cdba9.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.7.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7e7cb1c73dbbfc6b136260a0ca9bb2b96271e0a637511b3dc82afbbff751fa1c.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.7.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bcfeb2fab0256f468c2b564904fea39e499d071c42e4354e1f2dc0eebe364de1.packed",
"scales": "t_bcfeb2fab0256f468c2b564904fea39e499d071c42e4354e1f2dc0eebe364de1.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.7.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_f3240ada8e8b3eceeb3c4447c26fb66e92193f7c28cebbc06582e388d9ee28ed.packed",
"scales": "t_f3240ada8e8b3eceeb3c4447c26fb66e92193f7c28cebbc06582e388d9ee28ed.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.7.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_9388d5466ee325aa7c9489fed002aef97bc1894bce63c38ecc2b2647db2999b8.packed",
"scales": "t_9388d5466ee325aa7c9489fed002aef97bc1894bce63c38ecc2b2647db2999b8.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.7.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_51013759ab8a0b188743bf5f04658162fec6f4cf3221db802d78ec604a00efd2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.7.self_attn.k_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_93937c66103aa3d1b335b08b7e11004835432cbc9015452d6ef571b31ca83841.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.7.self_attn.k_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_08e4b14f410e1267aa8680aae76412b93f1efc1832af300e02189c53111476d6.packed",
"scales": "t_08e4b14f410e1267aa8680aae76412b93f1efc1832af300e02189c53111476d6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.7.self_attn.o_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ad9104e2bebf6001d650a0c5ba8f165b4cdc2ed853dc0dbcd620b7c849c5cb5f.packed",
"scales": "t_ad9104e2bebf6001d650a0c5ba8f165b4cdc2ed853dc0dbcd620b7c849c5cb5f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.7.self_attn.q_norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7a22eb440e7994db1a91a4f65cfc7387a2573da21572eb8b3efe945941412e2f.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
256
],
"version": 1
}
},
"model.layers.7.self_attn.q_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_807a9ec308e8d4aa8243767e6ea586f84871a0f4f51af04446bfd1cb112ccf2d.packed",
"scales": "t_807a9ec308e8d4aa8243767e6ea586f84871a0f4f51af04446bfd1cb112ccf2d.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
12288,
5120
],
"version": 1
}
},
"model.layers.7.self_attn.v_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c8a3ddab0be75bbca8d1ff935141565ad4ae7a0db31d38903f00455a21d58620.packed",
"scales": "t_c8a3ddab0be75bbca8d1ff935141565ad4ae7a0db31d38903f00455a21d58620.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
1024,
5120
],
"version": 1
}
},
"model.layers.8.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_adb917f1b34b47ce995f5a8a21c93d314252f65ec2d658087aa872a5b81d4778.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.8.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_76f86ae5451a7faaee7b46a4a2cf35fa83c390f45530bd11197af9b25f134bb4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.8.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e6bc1d6df3cf3075b2d613a1c9ba01c704f118e174b62cdfd029c1ce2bd5d348.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.8.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_6d494f3f20902ebc55126c1c82919607a63201a15af474b23ff1cae9d3f2d604.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.8.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_a830809bc0024343ac535edfba359d25369a54759536da544462a4ba5ff47568.packed",
"scales": "t_a830809bc0024343ac535edfba359d25369a54759536da544462a4ba5ff47568.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.8.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d18f841045ab7888edf4fb8b9a056a3a6dd014b662973d576f8fe4bbf929926f.packed",
"scales": "t_d18f841045ab7888edf4fb8b9a056a3a6dd014b662973d576f8fe4bbf929926f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.8.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ec8dccc5afac7c3809e1032885be236fba84157ae5adcca383ba983cc3f1aa53.packed",
"scales": "t_ec8dccc5afac7c3809e1032885be236fba84157ae5adcca383ba983cc3f1aa53.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.8.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_32555a54175132ef2fa1b4cc6798b32a50a7d2b1e35beeeafcdff9f8e517a1ff.packed",
"scales": "t_32555a54175132ef2fa1b4cc6798b32a50a7d2b1e35beeeafcdff9f8e517a1ff.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.8.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_077b521bf7fb0919533e59f37471e40cc5a250204203047afc670cc91e0b3dcd.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.8.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_fc6ee44ac29349e6f2366f25cee103ae88d531a841f7ec62429058bacd1fced0.packed",
"scales": "t_fc6ee44ac29349e6f2366f25cee103ae88d531a841f7ec62429058bacd1fced0.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.8.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_1cab8421288441095c30f901f8fb3590e3d31484dc796f6523ccf8da438ebbbb.packed",
"scales": "t_1cab8421288441095c30f901f8fb3590e3d31484dc796f6523ccf8da438ebbbb.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.8.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_b260592b83669cd102419087cf4f2b4951fd94c575680a8856c907a9dce0792f.packed",
"scales": "t_b260592b83669cd102419087cf4f2b4951fd94c575680a8856c907a9dce0792f.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.8.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_ac62f43ed13830e40ffa254ae4b9f596ab4f62074cf51feadb2bd18d7b4ff198.packed",
"scales": "t_ac62f43ed13830e40ffa254ae4b9f596ab4f62074cf51feadb2bd18d7b4ff198.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.8.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_1b431475e1fe31def59e2283188dc870453703068a8c0691bc7d22422a508ff1.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.9.input_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_3c434d00594c74ae727b2f6338dc643bb1083e1cdd93bffd14cf21d56110c5f8.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.layers.9.linear_attn.A_log": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e82f7f9bc0b166786d55970f5a2407a466339bd84cf3bcc6c7b133a782f02791.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.9.linear_attn.conv1d.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_f09d7737d497ba6ae7d3c9c192e9de296964ea5f328888afbb1aa75edce646d4.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
10240,
1,
4
],
"version": 1
}
},
"model.layers.9.linear_attn.dt_bias": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_e917a1cc93179ac2b8b6a4466779c1c83d75ef3108fbe0e48581b579bedcdf10.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
48
],
"version": 1
}
},
"model.layers.9.linear_attn.in_proj_a.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_c37bc93c72d65aed87f6a8beb79b1806b46dbaca64d16deb6c251c8cd504860e.packed",
"scales": "t_c37bc93c72d65aed87f6a8beb79b1806b46dbaca64d16deb6c251c8cd504860e.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.9.linear_attn.in_proj_b.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_559246f0c876d0e6e4831fe2a5c92707c30329c6f704e71daae5d116308d813a.packed",
"scales": "t_559246f0c876d0e6e4831fe2a5c92707c30329c6f704e71daae5d116308d813a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
48,
5120
],
"version": 1
}
},
"model.layers.9.linear_attn.in_proj_qkv.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_370030f8f65e3525ce469a2475518b61c5f6886e3517856485aa71da99e834b6.packed",
"scales": "t_370030f8f65e3525ce469a2475518b61c5f6886e3517856485aa71da99e834b6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
10240,
5120
],
"version": 1
}
},
"model.layers.9.linear_attn.in_proj_z.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_56c134e241719d64a0cf775c2df8f734d41d2c4d818bc479a38ad3f3af78953c.packed",
"scales": "t_56c134e241719d64a0cf775c2df8f734d41d2c4d818bc479a38ad3f3af78953c.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
6144,
5120
],
"version": 1
}
},
"model.layers.9.linear_attn.norm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_7d6743de8c40111c1d3359aafa20e56d2913a8189a3457b3bcfc2ad97c1a6488.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
128
],
"version": 1
}
},
"model.layers.9.linear_attn.out_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_bf65aa360a42a35ceae0964173bd6a135e1d30a41d731f6780cff8589325854a.packed",
"scales": "t_bf65aa360a42a35ceae0964173bd6a135e1d30a41d731f6780cff8589325854a.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
6144
],
"version": 1
}
},
"model.layers.9.mlp.down_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_38e29d41d97a337ac91d3d6e9a6a30157396a332dff59c70fc174eeb26a2a5b7.packed",
"scales": "t_38e29d41d97a337ac91d3d6e9a6a30157396a332dff59c70fc174eeb26a2a5b7.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
5120,
17408
],
"version": 1
}
},
"model.layers.9.mlp.gate_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_63f9d5fb75551fcc624b6cc25194bb399bca99039c6d6e54360d06910b5341c6.packed",
"scales": "t_63f9d5fb75551fcc624b6cc25194bb399bca99039c6d6e54360d06910b5341c6.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.9.mlp.up_proj.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"packed": "t_d024e6c453ee0d7a69abac55c28f56342de750c5f0120cdf4b76d76044477823.packed",
"scales": "t_d024e6c453ee0d7a69abac55c28f56342de750c5f0120cdf4b76d76044477823.scales"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 1,
"kind": "ternary",
"packed_group_bytes": 26,
"requested_group": 128,
"scale_dtype": "bfloat16",
"shape": [
17408,
5120
],
"version": 1
}
},
"model.layers.9.post_attention_layernorm.weight": {
"file": "compact-00001-of-00002.safetensors",
"payload": {
"weight": "t_841eebb1e36bbf4475f695b3a76504c33a4a8243690157ff5c3f8f1703197c9d.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
},
"model.norm.weight": {
"file": "compact-00002-of-00002.safetensors",
"payload": {
"weight": "t_4e709958f651ec86475062b76f4a263a85845361e019c63ff27c8ac63f56aec2.weight"
},
"spec": {
"dtype": "bfloat16",
"group": 128,
"k": 0,
"kind": "raw",
"requested_group": 128,
"shape": [
5120
],
"version": 1
}
}
},
"format": "attn-k2-mixed-v1",
"identity_hash": "2db7ab888981ac3b74713237356f2262bd22e8b3c6323ddaef4c782537482d98",
"raw_fallback": [],
"raw_nonmatrix_count": 353,
"stages": [
"body:model-00001-of-00002.safetensors",
"body:model-00002-of-00002.safetensors",
"head",
"index",
"complete"
],
"tensor_count": 851
}