WebGPU-CodeLlama-7b-hf-q4f32_1 / ndarray-cache.json
ClankPan26cm's picture
new compilation flow
2bfff89
Raw History Blame Contribute Delete
151 kB
{ "metadata": { "ParamSize": 325, "ParamBytes": 4212490240.0, "BitsPerParam": 5.001066770081567 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65568768, "records": [ { "name": "lm_head.q_weight", "shape": [ 32016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 65568768, "byteOffset": 0 } ], "md5sum": "0d2a47a0c4687331365f7c308194cdf6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "2b8b5bb60f7792fd1194ec704991c4b7" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "35c7c839822806017538edf814154d67" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ebb3bf010586bbf4c9290c2a3a1beec1" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 27713536, "records": [ { "name": "lm_head.q_scale", "shape": [ 32016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 16392192, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16392192 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 16408576 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22044672 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 22061056 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 22077440 } ], "md5sum": "a1daed8c212f0a37c07239524af61d12" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "dd144f97892730c55e86957cbca91d08" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "5dbb633d9f598d7bf693a8c54b690ac9" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "24f582069781315ad5c2085e4cf414b4" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "d313a96f20af4b1908aefb54cae8a474" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "00d59147847f690dc609ae129b0a7672" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "ac02b26138b35bf56011f79e78019d70" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "1c9eb1381e5d8077de55d42496368de8" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "478b5d500a2c2c2e2633c0a2b2920499" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f2be7b7f7b3d83d371f139aa14a3e18c" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bcc6bade5c067a9e524e6b3ca3ce88ad" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "46a137459b6ba25fc093d064d2293199" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "477bc475b9a67aaeffb392055780b652" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "00674b4872329bfe10b9e3e427da4e62" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "39e1a0b47432772a174dd7e458539b3d" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "1e2150c37f3fa055aea28f139c18a2b0" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "8061b26411658fe77c256e4126a30079" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "882b640b021e693f4b28b9facee130d6" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "584dbb1372234ef5fd4294c11e88039b" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "5e0f2a65848b10b0d33af5c86cd5f3e0" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "3361b6ea6a9917fa266d27095fcfe8d6" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "188856da72d666ea2ca3adcfdb072c00" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "15c28006ab87e604ecd44fdd99d28147" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "3cadccac583c3810b96fed3e2a6d8fdd" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "1966e45e9b5acf421ff4133b05d75236" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "900a239828d108eca7334b8c5e0b64fe" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "f4a6901f85e878f50996343d0cd5dbcb" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "9299e35a2e76c93cf3ab31a6013ab6d4" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "aa8ce9c339d2eab6c90fffaf6a7a2b28" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "eb54e366fe084f308628cf0d63263165" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "f697df9449bed76e96d03049b636f534" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 65568768, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 65568768, "byteOffset": 0 } ], "md5sum": "df470470c319fac0664b5d831d02cc5f" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e8613dec3955147e470b117c3b741480" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "b7b2fc735275f027638772fc5b19a07a" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 24158208, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 16392192, "byteOffset": 2113536 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 18505728 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 18522112 } ], "md5sum": "0305f1836a17b3c133f804b42a617751" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e57a6193d604bf7ee6eb742a2941f66e" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "687f2528834514a17b14fd2ab81b7d2b" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "91b8fade53286360f7c6539f1d67eecc" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "87594d02f0f5cde6f99772ca3209be1b" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "32ece1565b2bcb7df3e1353d6d20d1cf" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "8b41a97eb55bedd3de5e2ce5da19521c" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "c196b14e44e578b97356e9b1c512ea77" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "82fdbc556f62623c5dd5eecbe2837910" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "45dc579fe5e0a997a17bed7abe52465f" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "5e814bda36ae4aaeb815d94d75a3a351" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 28065792, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 } ], "md5sum": "af59b02e6276cb3bdaa3ff752c1a9d4e" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c27486fb0a80869086289c09a7c8e1c2" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "060c13254aa218736d3c995f2d3f7934" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 28065792, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11272192 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17563648 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25952256 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28049408 } ], "md5sum": "0d79a038ac2b02f8a8df3694d25ec3b8" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "19ab6e5268ec5a6b1bcc0c9a6606457a" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a52f6fb032489a19a9f7bf94d95b9c9f" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "27c692cc75591084d06d64d2e53881d4" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a5d5602df778fd8da8edd402a1ad3d9c" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "55019aa77c885098120c1e4702d2e9c9" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "214286650b913f8ce57f5255bf72de4f" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "7bae96b83d6e53a503fbbb8a8fbe8a24" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "33aa6d9287276c37be567e286eeffc3f" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "aad21fefac6b20bdae9ab21b302141c0" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9b95dd594bb056dc243f9c835dfdbd40" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "235778a39387a803f52f800b1d7beeeb" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "54ee89d7b75a760e02a14ea7e71b1eef" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "3ebfc0d2d4a273251a5caf431bc3a472" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1977b9aa9d1fa6b25793cbc949f1659f" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "7298d2abe25b065130a5b2d77c9c9e99" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "d3911ac899fc75576fa087ba6011d22e" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "3670b10e0b995078046207eee0966d99" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "efd5054ce903b93a37f49199aaf9d34b" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "b8ef828e284f3f0c11dcc97f6dff8ca0" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f06f6fdd834b222ebafb673c241abd12" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "5991a4f4468498795b0a38d9b29b91d5" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "cefc90b43792196a4975637252d542c5" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "9e0e2d6cb423e79f86baa65c845f66a7" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "a585dcaa75303bf951bf3b3608e98e62" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "52ad0f8ef746470f1a4e02485f8c74c0" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "df83bd6364c1a99b050412d02b9e7957" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "ce98f81e4ebd08af89613505b0a43e04" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "2bc29ed59a66a77ec2cba28c7be6a7bb" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "2084b9c6cf8bd88278518142da681984" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "646fd358247bebdb4fd285faa2da32cb" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "9f73e95b126d804236a42096308f305b" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "d12324af7e60f22cff73cb35cd4376ee" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 28213248, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 5636096 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 5652480 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 5668864 } ], "md5sum": "e8c911e37634db8241931d28a96d8aa3" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "0792e52e0bb622f147e88799da010180" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "82dec2dad3c14b21c685a86ce5ec6017" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "25ed776cfc52353b6564f4288c135a8a" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "3592814a47269090993beb0ce510de04" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "06a4ee493c0ceb91d7e89e199b448f7e" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e54ef8e098bb1ae06b3819b576cf6d1a" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "90fac99f864884d822f275fa93db7a87" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "a4a34f4af78b13f15996fa249ea33f8e" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e84771cfcb0ca494f5ed81f17bf9934e" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7ecf039a9721f1e58ae55f569299e3d0" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "2b2271a0e3add6baf43a193122511e98" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "df2be6859b302973c1acfcef8c04c332" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "8d9311b6cc46627eeb41008d48e27899" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d529ddc9f0524c6d17e09ce7459cf135" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "661b1b1217927f8d90284751d5933f87" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "f56b90260eed22a11459e6fe12ff961f" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a53b85c344c00d94054df1911e621a34" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "44edec086ab92d4095047faa36834b71" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "1ee17b1f979750cb85388d555706b53d" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "8ef63b95507cb8d9640eeab82e44fe80" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "83da41bdcaae7ee45d79341c8d3b17ec" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e2aa78dd4a8386b8511039869e35f34f" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ec3bc80522b568c7eeca26a7f39da314" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "6dbbe03f37866b45549212421d254d71" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "049c45acbd0b2bd918b246a5ac74b767" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "127286cde8319b56b5bc45822e7d532f" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "5e0586044ae6d870a195356d1d035fcb" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "793fb5e9b0836916158749de35acd819" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "8c3ff0be63d428faf959c8dc5b1bb555" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "28dc7ec986949cf83cc760f9cc6d7103" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "804246cdb8f2602a179571836c107275" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "fee448af314db6705b95f0c704de903b" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "c7bb08a9bf169b67804ce0ec22782895" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c3ee708e67ddf10c4e331d71455f7614" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "90a262142572dab6f7b046e71fd20bce" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f295e0102144fac772c28b669d699c54" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 30294016, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 2097152 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 2113536 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 24657920 } ], "md5sum": "eb19d2d2a255d9aebd26b888b4643547" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "898c817ad296fbc07c3657c05b1864c1" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "raw", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "4d1a3d3d02f89652b00c0a7a52fc35cc" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 28082176, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 11288576 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 17580032 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 25968640 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 28065792 } ], "md5sum": "418faf260f483fb42ea5944fef6ab1ee" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "42179f6d64e783d2596d6bc8c77b9fad" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0e3b0417d9df97c25c0692e091f93be2" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 31604736, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float32", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 5636096 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float32", "format": "raw", "nbytes": 16384, "byteOffset": 16908288 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 16924672 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 23216128 } ], "md5sum": "20dd9c746546ba325da9e857f9da3f67" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "48df17cd2f304bae79c5077d9ba19932" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d42172c540026a76a8169fd2855e3e7f" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 30146560, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float32", "format": "raw", "nbytes": 11272192, "byteOffset": 2097152 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float32", "format": "raw", "nbytes": 6291456, "byteOffset": 13369344 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "raw", "nbytes": 8388608, "byteOffset": 19660800 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float32", "format": "raw", "nbytes": 2097152, "byteOffset": 28049408 } ], "md5sum": "bf577512c83f51837aef1f010386356a" } ] }
{
"metadata": {
"ParamSize": 325,
"ParamBytes": 4212490240.0,
"BitsPerParam": 5.001066770081567
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 65568768,
"records": [
{
"name": "lm_head.q_weight",
"shape": [
32016,
512
],
"dtype": "uint32",
"format": "raw",
"nbytes": 65568768,
"byteOffset": 0
}
],
"md5sum": "0d2a47a0c4687331365f7c308194cdf6"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.23.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "raw",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "2b8b5bb60f7792fd1194ec704991c4b7"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 22544384,
"records": [
{
"name": "model.layers.24.mlp.down_proj.q_weight",
"shape": [
4096,
1376
],
"dtype": "uint32",
"format": "raw",
"nbytes": 22544384,
"byteOffset": 0
}
],
"md5sum": "35c7c839822806017538edf814154d67"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 45088768,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
22016,
512
],
"dtype": "uint32",
"format": "raw",
"nbytes": 45088768,
"byteOffset": 0
}
],
"md5sum": "ebb3bf010586bbf4c9290c2a3a1beec1"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 27713536,
"records": [
{
"name": "lm_head.q_scale",
"shape": [
32016,
128
],
"dtype": "float32",
"format": "raw",
"nbytes": 16392192,
"byteOffset": 0
},
{