diff --git "a/expansion_depth.json" "b/expansion_depth.json" deleted file mode 100644--- "a/expansion_depth.json" +++ /dev/null @@ -1,17623 +0,0 @@ -{ - "kind": "depth", - "src": "/mnt/nfs_share/JiRackDeltaNet_36b/expanded", - "layers_old": 64, - "layers_new": 128, - "hidden": 5120, - "intermediate": 26624, - "copies": [ - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1, - 1 - ], - "layout": [ - [ - 0, - false - ], - [ - 1, - false - ], - [ - 2, - false - ], - [ - 3, - false - ], - [ - 0, - true - ], - [ - 1, - true - ], - [ - 2, - true - ], - [ - 3, - true - ], - [ - 4, - false - ], - [ - 5, - false - ], - [ - 6, - false - ], - [ - 7, - false - ], - [ - 4, - true - ], - [ - 5, - true - ], - [ - 6, - true - ], - [ - 7, - true - ], - [ - 8, - false - ], - [ - 9, - false - ], - [ - 10, - false - ], - [ - 11, - false - ], - [ - 8, - true - ], - [ - 9, - true - ], - [ - 10, - true - ], - [ - 11, - true - ], - [ - 12, - false - ], - [ - 13, - false - ], - [ - 14, - false - ], - [ - 15, - false - ], - [ - 12, - true - ], - [ - 13, - true - ], - [ - 14, - true - ], - [ - 15, - true - ], - [ - 16, - false - ], - [ - 17, - false - ], - [ - 18, - false - ], - [ - 19, - false - ], - [ - 16, - true - ], - [ - 17, - true - ], - [ - 18, - true - ], - [ - 19, - true - ], - [ - 20, - false - ], - [ - 21, - false - ], - [ - 22, - false - ], - [ - 23, - false - ], - [ - 20, - true - ], - [ - 21, - true - ], - [ - 22, - true - ], - [ - 23, - true - ], - [ - 24, - false - ], - [ - 25, - false - ], - [ - 26, - false - ], - [ - 27, - false - ], - [ - 24, - true - ], - [ - 25, - true - ], - [ - 26, - true - ], - [ - 27, - true - ], - [ - 28, - false - ], - [ - 29, - false - ], - [ - 30, - false - ], - [ - 31, - false - ], - [ - 28, - true - ], - [ - 29, - true - ], - [ - 30, - true - ], - [ - 31, - true - ], - [ - 32, - false - ], - [ - 33, - false - ], - [ - 34, - false - ], - [ - 35, - false - ], - [ - 32, - true - ], - [ - 33, - true - ], - [ - 34, - true - ], - [ - 35, - true - ], - [ - 36, - false - ], - [ - 37, - false - ], - [ - 38, - false - ], - [ - 39, - false - ], - [ - 36, - true - ], - [ - 37, - true - ], - [ - 38, - true - ], - [ - 39, - true - ], - [ - 40, - false - ], - [ - 41, - false - ], - [ - 42, - false - ], - [ - 43, - false - ], - [ - 40, - true - ], - [ - 41, - true - ], - [ - 42, - true - ], - [ - 43, - true - ], - [ - 44, - false - ], - [ - 45, - false - ], - [ - 46, - false - ], - [ - 47, - false - ], - [ - 44, - true - ], - [ - 45, - true - ], - [ - 46, - true - ], - [ - 47, - true - ], - [ - 48, - false - ], - [ - 49, - false - ], - [ - 50, - false - ], - [ - 51, - false - ], - [ - 48, - true - ], - [ - 49, - true - ], - [ - 50, - true - ], - [ - 51, - true - ], - [ - 52, - false - ], - [ - 53, - false - ], - [ - 54, - false - ], - [ - 55, - false - ], - [ - 52, - true - ], - [ - 53, - true - ], - [ - 54, - true - ], - [ - 55, - true - ], - [ - 56, - false - ], - [ - 57, - false - ], - [ - 58, - false - ], - [ - 59, - false - ], - [ - 56, - true - ], - [ - 57, - true - ], - [ - 58, - true - ], - [ - 59, - true - ], - [ - 60, - false - ], - [ - 61, - false - ], - [ - 62, - false - ], - [ - 63, - false - ], - [ - 60, - true - ], - [ - 61, - true - ], - [ - 62, - true - ], - [ - 63, - true - ] - ], - "zeroed_in_copies": [ - "linear_attn.out_proj.weight", - "self_attn.o_proj.weight", - "mlp.down_proj.weight" - ], - "params_before": 36521952256, - "params_after": 69934845440, - "shards": 27, - "bytes": 139869690880, - "side_files": [ - "chat_template.jinja", - "config.json", - "gguf.txt", - "system_prompt.txt", - "tokenizer.json", - "tokenizer_config.json" - ], - "config_changes": [ - "layer_types: 64 entries -> 128 (same 3 linear + 1 full pattern)", - "num_hidden_layers: 64 -> 128" - ], - "model_file_diff": [ - "--- JiRackDeltaNet_27b.py", - "+++ JiRackDeltaNet_70b.py", - "@@ -52,2 +52,2 @@", - "-INTERMEDIATE_SIZE = 17408", - "-NUM_LAYERS = 64", - "+INTERMEDIATE_SIZE = 26624", - "+NUM_LAYERS = 128" - ], - "minutes": 8.5, - "recipe": [ - { - "key": "model.embed_tokens.weight", - "src": "model.embed_tokens.weight", - "op": "copy" - }, - { - "key": "model.layers.0.input_layernorm.weight", - "src": "model.layers.0.input_layernorm.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.A_log", - "src": "model.layers.0.linear_attn.A_log", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.conv1d.weight", - "src": "model.layers.0.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.dt_bias", - "src": "model.layers.0.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.in_proj_a.weight", - "src": "model.layers.0.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.in_proj_b.weight", - "src": "model.layers.0.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.in_proj_qkv.weight", - "src": "model.layers.0.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.in_proj_z.weight", - "src": "model.layers.0.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.norm.weight", - "src": "model.layers.0.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.linear_attn.out_proj.weight", - "src": "model.layers.0.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.mlp.down_proj.weight", - "src": "model.layers.0.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.mlp.gate_proj.weight", - "src": "model.layers.0.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.mlp.up_proj.weight", - "src": "model.layers.0.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.0.post_attention_layernorm.weight", - "src": "model.layers.0.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 0, - 0, - false - ] - }, - { - "key": "model.layers.1.input_layernorm.weight", - "src": "model.layers.1.input_layernorm.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.A_log", - "src": "model.layers.1.linear_attn.A_log", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.conv1d.weight", - "src": "model.layers.1.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.dt_bias", - "src": "model.layers.1.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.in_proj_a.weight", - "src": "model.layers.1.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.in_proj_b.weight", - "src": "model.layers.1.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.in_proj_qkv.weight", - "src": "model.layers.1.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.in_proj_z.weight", - "src": "model.layers.1.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.norm.weight", - "src": "model.layers.1.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.linear_attn.out_proj.weight", - "src": "model.layers.1.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.mlp.down_proj.weight", - "src": "model.layers.1.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.mlp.gate_proj.weight", - "src": "model.layers.1.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.mlp.up_proj.weight", - "src": "model.layers.1.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.1.post_attention_layernorm.weight", - "src": "model.layers.1.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 1, - 1, - false - ] - }, - { - "key": "model.layers.2.input_layernorm.weight", - "src": "model.layers.2.input_layernorm.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.A_log", - "src": "model.layers.2.linear_attn.A_log", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.conv1d.weight", - "src": "model.layers.2.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.dt_bias", - "src": "model.layers.2.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.in_proj_a.weight", - "src": "model.layers.2.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.in_proj_b.weight", - "src": "model.layers.2.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.in_proj_qkv.weight", - "src": "model.layers.2.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.in_proj_z.weight", - "src": "model.layers.2.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.norm.weight", - "src": "model.layers.2.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.linear_attn.out_proj.weight", - "src": "model.layers.2.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.mlp.down_proj.weight", - "src": "model.layers.2.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.mlp.gate_proj.weight", - "src": "model.layers.2.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.mlp.up_proj.weight", - "src": "model.layers.2.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.2.post_attention_layernorm.weight", - "src": "model.layers.2.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 2, - 2, - false - ] - }, - { - "key": "model.layers.3.input_layernorm.weight", - "src": "model.layers.3.input_layernorm.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.mlp.down_proj.weight", - "src": "model.layers.3.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.mlp.gate_proj.weight", - "src": "model.layers.3.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.mlp.up_proj.weight", - "src": "model.layers.3.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.post_attention_layernorm.weight", - "src": "model.layers.3.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.self_attn.k_norm.weight", - "src": "model.layers.3.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.self_attn.k_proj.weight", - "src": "model.layers.3.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.self_attn.o_proj.weight", - "src": "model.layers.3.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.self_attn.q_norm.weight", - "src": "model.layers.3.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.self_attn.q_proj.weight", - "src": "model.layers.3.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.3.self_attn.v_proj.weight", - "src": "model.layers.3.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 3, - 3, - false - ] - }, - { - "key": "model.layers.4.input_layernorm.weight", - "src": "model.layers.0.input_layernorm.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.A_log", - "src": "model.layers.0.linear_attn.A_log", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.conv1d.weight", - "src": "model.layers.0.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.dt_bias", - "src": "model.layers.0.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.in_proj_a.weight", - "src": "model.layers.0.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.in_proj_b.weight", - "src": "model.layers.0.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.in_proj_qkv.weight", - "src": "model.layers.0.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.in_proj_z.weight", - "src": "model.layers.0.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.norm.weight", - "src": "model.layers.0.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.linear_attn.out_proj.weight", - "src": "model.layers.0.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.mlp.down_proj.weight", - "src": "model.layers.0.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.mlp.gate_proj.weight", - "src": "model.layers.0.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.mlp.up_proj.weight", - "src": "model.layers.0.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.4.post_attention_layernorm.weight", - "src": "model.layers.0.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 4, - 0, - true - ] - }, - { - "key": "model.layers.5.input_layernorm.weight", - "src": "model.layers.1.input_layernorm.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.A_log", - "src": "model.layers.1.linear_attn.A_log", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.conv1d.weight", - "src": "model.layers.1.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.dt_bias", - "src": "model.layers.1.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.in_proj_a.weight", - "src": "model.layers.1.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.in_proj_b.weight", - "src": "model.layers.1.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.in_proj_qkv.weight", - "src": "model.layers.1.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.in_proj_z.weight", - "src": "model.layers.1.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.norm.weight", - "src": "model.layers.1.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.linear_attn.out_proj.weight", - "src": "model.layers.1.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.mlp.down_proj.weight", - "src": "model.layers.1.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.mlp.gate_proj.weight", - "src": "model.layers.1.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.mlp.up_proj.weight", - "src": "model.layers.1.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.5.post_attention_layernorm.weight", - "src": "model.layers.1.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 5, - 1, - true - ] - }, - { - "key": "model.layers.6.input_layernorm.weight", - "src": "model.layers.2.input_layernorm.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.A_log", - "src": "model.layers.2.linear_attn.A_log", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.conv1d.weight", - "src": "model.layers.2.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.dt_bias", - "src": "model.layers.2.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.in_proj_a.weight", - "src": "model.layers.2.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.in_proj_b.weight", - "src": "model.layers.2.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.in_proj_qkv.weight", - "src": "model.layers.2.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.in_proj_z.weight", - "src": "model.layers.2.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.norm.weight", - "src": "model.layers.2.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.linear_attn.out_proj.weight", - "src": "model.layers.2.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.mlp.down_proj.weight", - "src": "model.layers.2.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.mlp.gate_proj.weight", - "src": "model.layers.2.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.mlp.up_proj.weight", - "src": "model.layers.2.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.6.post_attention_layernorm.weight", - "src": "model.layers.2.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 6, - 2, - true - ] - }, - { - "key": "model.layers.7.input_layernorm.weight", - "src": "model.layers.3.input_layernorm.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.mlp.down_proj.weight", - "src": "model.layers.3.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.mlp.gate_proj.weight", - "src": "model.layers.3.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.mlp.up_proj.weight", - "src": "model.layers.3.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.post_attention_layernorm.weight", - "src": "model.layers.3.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.self_attn.k_norm.weight", - "src": "model.layers.3.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.self_attn.k_proj.weight", - "src": "model.layers.3.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.self_attn.o_proj.weight", - "src": "model.layers.3.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.self_attn.q_norm.weight", - "src": "model.layers.3.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.self_attn.q_proj.weight", - "src": "model.layers.3.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.7.self_attn.v_proj.weight", - "src": "model.layers.3.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 7, - 3, - true - ] - }, - { - "key": "model.layers.8.input_layernorm.weight", - "src": "model.layers.4.input_layernorm.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.A_log", - "src": "model.layers.4.linear_attn.A_log", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.conv1d.weight", - "src": "model.layers.4.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.dt_bias", - "src": "model.layers.4.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.in_proj_a.weight", - "src": "model.layers.4.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.in_proj_b.weight", - "src": "model.layers.4.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.in_proj_qkv.weight", - "src": "model.layers.4.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.in_proj_z.weight", - "src": "model.layers.4.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.norm.weight", - "src": "model.layers.4.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.linear_attn.out_proj.weight", - "src": "model.layers.4.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.mlp.down_proj.weight", - "src": "model.layers.4.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.mlp.gate_proj.weight", - "src": "model.layers.4.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.mlp.up_proj.weight", - "src": "model.layers.4.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.8.post_attention_layernorm.weight", - "src": "model.layers.4.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 8, - 4, - false - ] - }, - { - "key": "model.layers.9.input_layernorm.weight", - "src": "model.layers.5.input_layernorm.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.A_log", - "src": "model.layers.5.linear_attn.A_log", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.conv1d.weight", - "src": "model.layers.5.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.dt_bias", - "src": "model.layers.5.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.in_proj_a.weight", - "src": "model.layers.5.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.in_proj_b.weight", - "src": "model.layers.5.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.in_proj_qkv.weight", - "src": "model.layers.5.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.in_proj_z.weight", - "src": "model.layers.5.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.norm.weight", - "src": "model.layers.5.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.linear_attn.out_proj.weight", - "src": "model.layers.5.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.mlp.down_proj.weight", - "src": "model.layers.5.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.mlp.gate_proj.weight", - "src": "model.layers.5.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.mlp.up_proj.weight", - "src": "model.layers.5.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.9.post_attention_layernorm.weight", - "src": "model.layers.5.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 9, - 5, - false - ] - }, - { - "key": "model.layers.10.input_layernorm.weight", - "src": "model.layers.6.input_layernorm.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.A_log", - "src": "model.layers.6.linear_attn.A_log", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.conv1d.weight", - "src": "model.layers.6.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.dt_bias", - "src": "model.layers.6.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.in_proj_a.weight", - "src": "model.layers.6.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.in_proj_b.weight", - "src": "model.layers.6.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.in_proj_qkv.weight", - "src": "model.layers.6.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.in_proj_z.weight", - "src": "model.layers.6.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.norm.weight", - "src": "model.layers.6.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.linear_attn.out_proj.weight", - "src": "model.layers.6.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.mlp.down_proj.weight", - "src": "model.layers.6.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.mlp.gate_proj.weight", - "src": "model.layers.6.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.mlp.up_proj.weight", - "src": "model.layers.6.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.10.post_attention_layernorm.weight", - "src": "model.layers.6.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 10, - 6, - false - ] - }, - { - "key": "model.layers.11.input_layernorm.weight", - "src": "model.layers.7.input_layernorm.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.mlp.down_proj.weight", - "src": "model.layers.7.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.mlp.gate_proj.weight", - "src": "model.layers.7.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.mlp.up_proj.weight", - "src": "model.layers.7.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.post_attention_layernorm.weight", - "src": "model.layers.7.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.self_attn.k_norm.weight", - "src": "model.layers.7.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.self_attn.k_proj.weight", - "src": "model.layers.7.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.self_attn.o_proj.weight", - "src": "model.layers.7.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.self_attn.q_norm.weight", - "src": "model.layers.7.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.self_attn.q_proj.weight", - "src": "model.layers.7.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.11.self_attn.v_proj.weight", - "src": "model.layers.7.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 11, - 7, - false - ] - }, - { - "key": "model.layers.12.input_layernorm.weight", - "src": "model.layers.4.input_layernorm.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.A_log", - "src": "model.layers.4.linear_attn.A_log", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.conv1d.weight", - "src": "model.layers.4.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.dt_bias", - "src": "model.layers.4.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.in_proj_a.weight", - "src": "model.layers.4.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.in_proj_b.weight", - "src": "model.layers.4.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.in_proj_qkv.weight", - "src": "model.layers.4.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.in_proj_z.weight", - "src": "model.layers.4.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.norm.weight", - "src": "model.layers.4.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.linear_attn.out_proj.weight", - "src": "model.layers.4.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.mlp.down_proj.weight", - "src": "model.layers.4.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.mlp.gate_proj.weight", - "src": "model.layers.4.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.mlp.up_proj.weight", - "src": "model.layers.4.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.12.post_attention_layernorm.weight", - "src": "model.layers.4.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 12, - 4, - true - ] - }, - { - "key": "model.layers.13.input_layernorm.weight", - "src": "model.layers.5.input_layernorm.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.A_log", - "src": "model.layers.5.linear_attn.A_log", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.conv1d.weight", - "src": "model.layers.5.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.dt_bias", - "src": "model.layers.5.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.in_proj_a.weight", - "src": "model.layers.5.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.in_proj_b.weight", - "src": "model.layers.5.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.in_proj_qkv.weight", - "src": "model.layers.5.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.in_proj_z.weight", - "src": "model.layers.5.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.norm.weight", - "src": "model.layers.5.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.linear_attn.out_proj.weight", - "src": "model.layers.5.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.mlp.down_proj.weight", - "src": "model.layers.5.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.mlp.gate_proj.weight", - "src": "model.layers.5.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.mlp.up_proj.weight", - "src": "model.layers.5.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.13.post_attention_layernorm.weight", - "src": "model.layers.5.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 13, - 5, - true - ] - }, - { - "key": "model.layers.14.input_layernorm.weight", - "src": "model.layers.6.input_layernorm.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.A_log", - "src": "model.layers.6.linear_attn.A_log", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.conv1d.weight", - "src": "model.layers.6.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.dt_bias", - "src": "model.layers.6.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.in_proj_a.weight", - "src": "model.layers.6.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.in_proj_b.weight", - "src": "model.layers.6.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.in_proj_qkv.weight", - "src": "model.layers.6.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.in_proj_z.weight", - "src": "model.layers.6.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.norm.weight", - "src": "model.layers.6.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.linear_attn.out_proj.weight", - "src": "model.layers.6.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.mlp.down_proj.weight", - "src": "model.layers.6.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.mlp.gate_proj.weight", - "src": "model.layers.6.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.mlp.up_proj.weight", - "src": "model.layers.6.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.14.post_attention_layernorm.weight", - "src": "model.layers.6.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 14, - 6, - true - ] - }, - { - "key": "model.layers.15.input_layernorm.weight", - "src": "model.layers.7.input_layernorm.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.mlp.down_proj.weight", - "src": "model.layers.7.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.mlp.gate_proj.weight", - "src": "model.layers.7.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.mlp.up_proj.weight", - "src": "model.layers.7.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.post_attention_layernorm.weight", - "src": "model.layers.7.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.self_attn.k_norm.weight", - "src": "model.layers.7.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.self_attn.k_proj.weight", - "src": "model.layers.7.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.self_attn.o_proj.weight", - "src": "model.layers.7.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.self_attn.q_norm.weight", - "src": "model.layers.7.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.self_attn.q_proj.weight", - "src": "model.layers.7.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.15.self_attn.v_proj.weight", - "src": "model.layers.7.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 15, - 7, - true - ] - }, - { - "key": "model.layers.16.input_layernorm.weight", - "src": "model.layers.8.input_layernorm.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.A_log", - "src": "model.layers.8.linear_attn.A_log", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.conv1d.weight", - "src": "model.layers.8.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.dt_bias", - "src": "model.layers.8.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.in_proj_a.weight", - "src": "model.layers.8.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.in_proj_b.weight", - "src": "model.layers.8.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.in_proj_qkv.weight", - "src": "model.layers.8.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.in_proj_z.weight", - "src": "model.layers.8.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.norm.weight", - "src": "model.layers.8.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.linear_attn.out_proj.weight", - "src": "model.layers.8.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.mlp.down_proj.weight", - "src": "model.layers.8.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.mlp.gate_proj.weight", - "src": "model.layers.8.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.mlp.up_proj.weight", - "src": "model.layers.8.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.16.post_attention_layernorm.weight", - "src": "model.layers.8.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 16, - 8, - false - ] - }, - { - "key": "model.layers.17.input_layernorm.weight", - "src": "model.layers.9.input_layernorm.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.A_log", - "src": "model.layers.9.linear_attn.A_log", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.conv1d.weight", - "src": "model.layers.9.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.dt_bias", - "src": "model.layers.9.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.in_proj_a.weight", - "src": "model.layers.9.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.in_proj_b.weight", - "src": "model.layers.9.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.in_proj_qkv.weight", - "src": "model.layers.9.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.in_proj_z.weight", - "src": "model.layers.9.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.norm.weight", - "src": "model.layers.9.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.linear_attn.out_proj.weight", - "src": "model.layers.9.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.mlp.down_proj.weight", - "src": "model.layers.9.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.mlp.gate_proj.weight", - "src": "model.layers.9.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.mlp.up_proj.weight", - "src": "model.layers.9.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.17.post_attention_layernorm.weight", - "src": "model.layers.9.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 17, - 9, - false - ] - }, - { - "key": "model.layers.18.input_layernorm.weight", - "src": "model.layers.10.input_layernorm.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.A_log", - "src": "model.layers.10.linear_attn.A_log", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.conv1d.weight", - "src": "model.layers.10.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.dt_bias", - "src": "model.layers.10.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.in_proj_a.weight", - "src": "model.layers.10.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.in_proj_b.weight", - "src": "model.layers.10.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.in_proj_qkv.weight", - "src": "model.layers.10.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.in_proj_z.weight", - "src": "model.layers.10.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.norm.weight", - "src": "model.layers.10.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.linear_attn.out_proj.weight", - "src": "model.layers.10.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.mlp.down_proj.weight", - "src": "model.layers.10.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.mlp.gate_proj.weight", - "src": "model.layers.10.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.mlp.up_proj.weight", - "src": "model.layers.10.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.18.post_attention_layernorm.weight", - "src": "model.layers.10.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 18, - 10, - false - ] - }, - { - "key": "model.layers.19.input_layernorm.weight", - "src": "model.layers.11.input_layernorm.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.mlp.down_proj.weight", - "src": "model.layers.11.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.mlp.gate_proj.weight", - "src": "model.layers.11.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.mlp.up_proj.weight", - "src": "model.layers.11.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.post_attention_layernorm.weight", - "src": "model.layers.11.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.self_attn.k_norm.weight", - "src": "model.layers.11.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.self_attn.k_proj.weight", - "src": "model.layers.11.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.self_attn.o_proj.weight", - "src": "model.layers.11.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.self_attn.q_norm.weight", - "src": "model.layers.11.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.self_attn.q_proj.weight", - "src": "model.layers.11.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.19.self_attn.v_proj.weight", - "src": "model.layers.11.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 19, - 11, - false - ] - }, - { - "key": "model.layers.20.input_layernorm.weight", - "src": "model.layers.8.input_layernorm.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.A_log", - "src": "model.layers.8.linear_attn.A_log", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.conv1d.weight", - "src": "model.layers.8.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.dt_bias", - "src": "model.layers.8.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.in_proj_a.weight", - "src": "model.layers.8.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.in_proj_b.weight", - "src": "model.layers.8.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.in_proj_qkv.weight", - "src": "model.layers.8.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.in_proj_z.weight", - "src": "model.layers.8.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.norm.weight", - "src": "model.layers.8.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.linear_attn.out_proj.weight", - "src": "model.layers.8.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.mlp.down_proj.weight", - "src": "model.layers.8.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.mlp.gate_proj.weight", - "src": "model.layers.8.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.mlp.up_proj.weight", - "src": "model.layers.8.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.20.post_attention_layernorm.weight", - "src": "model.layers.8.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 20, - 8, - true - ] - }, - { - "key": "model.layers.21.input_layernorm.weight", - "src": "model.layers.9.input_layernorm.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.A_log", - "src": "model.layers.9.linear_attn.A_log", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.conv1d.weight", - "src": "model.layers.9.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.dt_bias", - "src": "model.layers.9.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.in_proj_a.weight", - "src": "model.layers.9.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.in_proj_b.weight", - "src": "model.layers.9.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.in_proj_qkv.weight", - "src": "model.layers.9.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.in_proj_z.weight", - "src": "model.layers.9.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.norm.weight", - "src": "model.layers.9.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.linear_attn.out_proj.weight", - "src": "model.layers.9.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.mlp.down_proj.weight", - "src": "model.layers.9.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.mlp.gate_proj.weight", - "src": "model.layers.9.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.mlp.up_proj.weight", - "src": "model.layers.9.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.21.post_attention_layernorm.weight", - "src": "model.layers.9.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 21, - 9, - true - ] - }, - { - "key": "model.layers.22.input_layernorm.weight", - "src": "model.layers.10.input_layernorm.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.A_log", - "src": "model.layers.10.linear_attn.A_log", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.conv1d.weight", - "src": "model.layers.10.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.dt_bias", - "src": "model.layers.10.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.in_proj_a.weight", - "src": "model.layers.10.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.in_proj_b.weight", - "src": "model.layers.10.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.in_proj_qkv.weight", - "src": "model.layers.10.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.in_proj_z.weight", - "src": "model.layers.10.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.norm.weight", - "src": "model.layers.10.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.linear_attn.out_proj.weight", - "src": "model.layers.10.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.mlp.down_proj.weight", - "src": "model.layers.10.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.mlp.gate_proj.weight", - "src": "model.layers.10.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.mlp.up_proj.weight", - "src": "model.layers.10.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.22.post_attention_layernorm.weight", - "src": "model.layers.10.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 22, - 10, - true - ] - }, - { - "key": "model.layers.23.input_layernorm.weight", - "src": "model.layers.11.input_layernorm.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.mlp.down_proj.weight", - "src": "model.layers.11.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.mlp.gate_proj.weight", - "src": "model.layers.11.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.mlp.up_proj.weight", - "src": "model.layers.11.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.post_attention_layernorm.weight", - "src": "model.layers.11.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.self_attn.k_norm.weight", - "src": "model.layers.11.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.self_attn.k_proj.weight", - "src": "model.layers.11.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.self_attn.o_proj.weight", - "src": "model.layers.11.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.self_attn.q_norm.weight", - "src": "model.layers.11.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.self_attn.q_proj.weight", - "src": "model.layers.11.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.23.self_attn.v_proj.weight", - "src": "model.layers.11.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 23, - 11, - true - ] - }, - { - "key": "model.layers.24.input_layernorm.weight", - "src": "model.layers.12.input_layernorm.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.A_log", - "src": "model.layers.12.linear_attn.A_log", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.conv1d.weight", - "src": "model.layers.12.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.dt_bias", - "src": "model.layers.12.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.in_proj_a.weight", - "src": "model.layers.12.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.in_proj_b.weight", - "src": "model.layers.12.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.in_proj_qkv.weight", - "src": "model.layers.12.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.in_proj_z.weight", - "src": "model.layers.12.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.norm.weight", - "src": "model.layers.12.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.linear_attn.out_proj.weight", - "src": "model.layers.12.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.mlp.down_proj.weight", - "src": "model.layers.12.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.mlp.gate_proj.weight", - "src": "model.layers.12.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.mlp.up_proj.weight", - "src": "model.layers.12.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.24.post_attention_layernorm.weight", - "src": "model.layers.12.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 24, - 12, - false - ] - }, - { - "key": "model.layers.25.input_layernorm.weight", - "src": "model.layers.13.input_layernorm.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.A_log", - "src": "model.layers.13.linear_attn.A_log", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.conv1d.weight", - "src": "model.layers.13.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.dt_bias", - "src": "model.layers.13.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.in_proj_a.weight", - "src": "model.layers.13.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.in_proj_b.weight", - "src": "model.layers.13.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.in_proj_qkv.weight", - "src": "model.layers.13.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.in_proj_z.weight", - "src": "model.layers.13.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.norm.weight", - "src": "model.layers.13.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.linear_attn.out_proj.weight", - "src": "model.layers.13.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.mlp.down_proj.weight", - "src": "model.layers.13.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.mlp.gate_proj.weight", - "src": "model.layers.13.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.mlp.up_proj.weight", - "src": "model.layers.13.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.25.post_attention_layernorm.weight", - "src": "model.layers.13.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 25, - 13, - false - ] - }, - { - "key": "model.layers.26.input_layernorm.weight", - "src": "model.layers.14.input_layernorm.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.A_log", - "src": "model.layers.14.linear_attn.A_log", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.conv1d.weight", - "src": "model.layers.14.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.dt_bias", - "src": "model.layers.14.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.in_proj_a.weight", - "src": "model.layers.14.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.in_proj_b.weight", - "src": "model.layers.14.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.in_proj_qkv.weight", - "src": "model.layers.14.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.in_proj_z.weight", - "src": "model.layers.14.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.norm.weight", - "src": "model.layers.14.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.linear_attn.out_proj.weight", - "src": "model.layers.14.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.mlp.down_proj.weight", - "src": "model.layers.14.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.mlp.gate_proj.weight", - "src": "model.layers.14.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.mlp.up_proj.weight", - "src": "model.layers.14.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.26.post_attention_layernorm.weight", - "src": "model.layers.14.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 26, - 14, - false - ] - }, - { - "key": "model.layers.27.input_layernorm.weight", - "src": "model.layers.15.input_layernorm.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.mlp.down_proj.weight", - "src": "model.layers.15.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.mlp.gate_proj.weight", - "src": "model.layers.15.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.mlp.up_proj.weight", - "src": "model.layers.15.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.post_attention_layernorm.weight", - "src": "model.layers.15.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.self_attn.k_norm.weight", - "src": "model.layers.15.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.self_attn.k_proj.weight", - "src": "model.layers.15.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.self_attn.o_proj.weight", - "src": "model.layers.15.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.self_attn.q_norm.weight", - "src": "model.layers.15.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.self_attn.q_proj.weight", - "src": "model.layers.15.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.27.self_attn.v_proj.weight", - "src": "model.layers.15.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 27, - 15, - false - ] - }, - { - "key": "model.layers.28.input_layernorm.weight", - "src": "model.layers.12.input_layernorm.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.A_log", - "src": "model.layers.12.linear_attn.A_log", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.conv1d.weight", - "src": "model.layers.12.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.dt_bias", - "src": "model.layers.12.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.in_proj_a.weight", - "src": "model.layers.12.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.in_proj_b.weight", - "src": "model.layers.12.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.in_proj_qkv.weight", - "src": "model.layers.12.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.in_proj_z.weight", - "src": "model.layers.12.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.norm.weight", - "src": "model.layers.12.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.linear_attn.out_proj.weight", - "src": "model.layers.12.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.mlp.down_proj.weight", - "src": "model.layers.12.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.mlp.gate_proj.weight", - "src": "model.layers.12.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.mlp.up_proj.weight", - "src": "model.layers.12.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.28.post_attention_layernorm.weight", - "src": "model.layers.12.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 28, - 12, - true - ] - }, - { - "key": "model.layers.29.input_layernorm.weight", - "src": "model.layers.13.input_layernorm.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.A_log", - "src": "model.layers.13.linear_attn.A_log", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.conv1d.weight", - "src": "model.layers.13.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.dt_bias", - "src": "model.layers.13.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.in_proj_a.weight", - "src": "model.layers.13.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.in_proj_b.weight", - "src": "model.layers.13.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.in_proj_qkv.weight", - "src": "model.layers.13.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.in_proj_z.weight", - "src": "model.layers.13.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.norm.weight", - "src": "model.layers.13.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.linear_attn.out_proj.weight", - "src": "model.layers.13.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.mlp.down_proj.weight", - "src": "model.layers.13.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.mlp.gate_proj.weight", - "src": "model.layers.13.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.mlp.up_proj.weight", - "src": "model.layers.13.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.29.post_attention_layernorm.weight", - "src": "model.layers.13.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 29, - 13, - true - ] - }, - { - "key": "model.layers.30.input_layernorm.weight", - "src": "model.layers.14.input_layernorm.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.A_log", - "src": "model.layers.14.linear_attn.A_log", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.conv1d.weight", - "src": "model.layers.14.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.dt_bias", - "src": "model.layers.14.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.in_proj_a.weight", - "src": "model.layers.14.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.in_proj_b.weight", - "src": "model.layers.14.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.in_proj_qkv.weight", - "src": "model.layers.14.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.in_proj_z.weight", - "src": "model.layers.14.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.norm.weight", - "src": "model.layers.14.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.linear_attn.out_proj.weight", - "src": "model.layers.14.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.mlp.down_proj.weight", - "src": "model.layers.14.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.mlp.gate_proj.weight", - "src": "model.layers.14.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.mlp.up_proj.weight", - "src": "model.layers.14.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.30.post_attention_layernorm.weight", - "src": "model.layers.14.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 30, - 14, - true - ] - }, - { - "key": "model.layers.31.input_layernorm.weight", - "src": "model.layers.15.input_layernorm.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.mlp.down_proj.weight", - "src": "model.layers.15.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.mlp.gate_proj.weight", - "src": "model.layers.15.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.mlp.up_proj.weight", - "src": "model.layers.15.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.post_attention_layernorm.weight", - "src": "model.layers.15.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.self_attn.k_norm.weight", - "src": "model.layers.15.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.self_attn.k_proj.weight", - "src": "model.layers.15.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.self_attn.o_proj.weight", - "src": "model.layers.15.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.self_attn.q_norm.weight", - "src": "model.layers.15.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.self_attn.q_proj.weight", - "src": "model.layers.15.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.31.self_attn.v_proj.weight", - "src": "model.layers.15.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 31, - 15, - true - ] - }, - { - "key": "model.layers.32.input_layernorm.weight", - "src": "model.layers.16.input_layernorm.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.A_log", - "src": "model.layers.16.linear_attn.A_log", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.conv1d.weight", - "src": "model.layers.16.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.dt_bias", - "src": "model.layers.16.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.in_proj_a.weight", - "src": "model.layers.16.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.in_proj_b.weight", - "src": "model.layers.16.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.in_proj_qkv.weight", - "src": "model.layers.16.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.in_proj_z.weight", - "src": "model.layers.16.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.norm.weight", - "src": "model.layers.16.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.linear_attn.out_proj.weight", - "src": "model.layers.16.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.mlp.down_proj.weight", - "src": "model.layers.16.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.mlp.gate_proj.weight", - "src": "model.layers.16.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.mlp.up_proj.weight", - "src": "model.layers.16.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.32.post_attention_layernorm.weight", - "src": "model.layers.16.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 32, - 16, - false - ] - }, - { - "key": "model.layers.33.input_layernorm.weight", - "src": "model.layers.17.input_layernorm.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.A_log", - "src": "model.layers.17.linear_attn.A_log", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.conv1d.weight", - "src": "model.layers.17.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.dt_bias", - "src": "model.layers.17.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.in_proj_a.weight", - "src": "model.layers.17.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.in_proj_b.weight", - "src": "model.layers.17.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.in_proj_qkv.weight", - "src": "model.layers.17.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.in_proj_z.weight", - "src": "model.layers.17.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.norm.weight", - "src": "model.layers.17.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.linear_attn.out_proj.weight", - "src": "model.layers.17.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.mlp.down_proj.weight", - "src": "model.layers.17.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.mlp.gate_proj.weight", - "src": "model.layers.17.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.mlp.up_proj.weight", - "src": "model.layers.17.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.33.post_attention_layernorm.weight", - "src": "model.layers.17.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 33, - 17, - false - ] - }, - { - "key": "model.layers.34.input_layernorm.weight", - "src": "model.layers.18.input_layernorm.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.A_log", - "src": "model.layers.18.linear_attn.A_log", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.conv1d.weight", - "src": "model.layers.18.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.dt_bias", - "src": "model.layers.18.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.in_proj_a.weight", - "src": "model.layers.18.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.in_proj_b.weight", - "src": "model.layers.18.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.in_proj_qkv.weight", - "src": "model.layers.18.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.in_proj_z.weight", - "src": "model.layers.18.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.norm.weight", - "src": "model.layers.18.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.linear_attn.out_proj.weight", - "src": "model.layers.18.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.mlp.down_proj.weight", - "src": "model.layers.18.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.mlp.gate_proj.weight", - "src": "model.layers.18.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.mlp.up_proj.weight", - "src": "model.layers.18.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.34.post_attention_layernorm.weight", - "src": "model.layers.18.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 34, - 18, - false - ] - }, - { - "key": "model.layers.35.input_layernorm.weight", - "src": "model.layers.19.input_layernorm.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.mlp.down_proj.weight", - "src": "model.layers.19.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.mlp.gate_proj.weight", - "src": "model.layers.19.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.mlp.up_proj.weight", - "src": "model.layers.19.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.post_attention_layernorm.weight", - "src": "model.layers.19.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.self_attn.k_norm.weight", - "src": "model.layers.19.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.self_attn.k_proj.weight", - "src": "model.layers.19.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.self_attn.o_proj.weight", - "src": "model.layers.19.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.self_attn.q_norm.weight", - "src": "model.layers.19.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.self_attn.q_proj.weight", - "src": "model.layers.19.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.35.self_attn.v_proj.weight", - "src": "model.layers.19.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 35, - 19, - false - ] - }, - { - "key": "model.layers.36.input_layernorm.weight", - "src": "model.layers.16.input_layernorm.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.A_log", - "src": "model.layers.16.linear_attn.A_log", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.conv1d.weight", - "src": "model.layers.16.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.dt_bias", - "src": "model.layers.16.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.in_proj_a.weight", - "src": "model.layers.16.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.in_proj_b.weight", - "src": "model.layers.16.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.in_proj_qkv.weight", - "src": "model.layers.16.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.in_proj_z.weight", - "src": "model.layers.16.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.norm.weight", - "src": "model.layers.16.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.linear_attn.out_proj.weight", - "src": "model.layers.16.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.mlp.down_proj.weight", - "src": "model.layers.16.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.mlp.gate_proj.weight", - "src": "model.layers.16.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.mlp.up_proj.weight", - "src": "model.layers.16.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.36.post_attention_layernorm.weight", - "src": "model.layers.16.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 36, - 16, - true - ] - }, - { - "key": "model.layers.37.input_layernorm.weight", - "src": "model.layers.17.input_layernorm.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.A_log", - "src": "model.layers.17.linear_attn.A_log", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.conv1d.weight", - "src": "model.layers.17.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.dt_bias", - "src": "model.layers.17.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.in_proj_a.weight", - "src": "model.layers.17.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.in_proj_b.weight", - "src": "model.layers.17.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.in_proj_qkv.weight", - "src": "model.layers.17.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.in_proj_z.weight", - "src": "model.layers.17.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.norm.weight", - "src": "model.layers.17.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.linear_attn.out_proj.weight", - "src": "model.layers.17.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.mlp.down_proj.weight", - "src": "model.layers.17.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.mlp.gate_proj.weight", - "src": "model.layers.17.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.mlp.up_proj.weight", - "src": "model.layers.17.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.37.post_attention_layernorm.weight", - "src": "model.layers.17.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 37, - 17, - true - ] - }, - { - "key": "model.layers.38.input_layernorm.weight", - "src": "model.layers.18.input_layernorm.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.A_log", - "src": "model.layers.18.linear_attn.A_log", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.conv1d.weight", - "src": "model.layers.18.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.dt_bias", - "src": "model.layers.18.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.in_proj_a.weight", - "src": "model.layers.18.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.in_proj_b.weight", - "src": "model.layers.18.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.in_proj_qkv.weight", - "src": "model.layers.18.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.in_proj_z.weight", - "src": "model.layers.18.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.norm.weight", - "src": "model.layers.18.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.linear_attn.out_proj.weight", - "src": "model.layers.18.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.mlp.down_proj.weight", - "src": "model.layers.18.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.mlp.gate_proj.weight", - "src": "model.layers.18.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.mlp.up_proj.weight", - "src": "model.layers.18.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.38.post_attention_layernorm.weight", - "src": "model.layers.18.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 38, - 18, - true - ] - }, - { - "key": "model.layers.39.input_layernorm.weight", - "src": "model.layers.19.input_layernorm.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.mlp.down_proj.weight", - "src": "model.layers.19.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.mlp.gate_proj.weight", - "src": "model.layers.19.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.mlp.up_proj.weight", - "src": "model.layers.19.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.post_attention_layernorm.weight", - "src": "model.layers.19.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.self_attn.k_norm.weight", - "src": "model.layers.19.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.self_attn.k_proj.weight", - "src": "model.layers.19.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.self_attn.o_proj.weight", - "src": "model.layers.19.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.self_attn.q_norm.weight", - "src": "model.layers.19.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.self_attn.q_proj.weight", - "src": "model.layers.19.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.39.self_attn.v_proj.weight", - "src": "model.layers.19.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 39, - 19, - true - ] - }, - { - "key": "model.layers.40.input_layernorm.weight", - "src": "model.layers.20.input_layernorm.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.A_log", - "src": "model.layers.20.linear_attn.A_log", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.conv1d.weight", - "src": "model.layers.20.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.dt_bias", - "src": "model.layers.20.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.in_proj_a.weight", - "src": "model.layers.20.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.in_proj_b.weight", - "src": "model.layers.20.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.in_proj_qkv.weight", - "src": "model.layers.20.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.in_proj_z.weight", - "src": "model.layers.20.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.norm.weight", - "src": "model.layers.20.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.linear_attn.out_proj.weight", - "src": "model.layers.20.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.mlp.down_proj.weight", - "src": "model.layers.20.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.mlp.gate_proj.weight", - "src": "model.layers.20.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.mlp.up_proj.weight", - "src": "model.layers.20.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.40.post_attention_layernorm.weight", - "src": "model.layers.20.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 40, - 20, - false - ] - }, - { - "key": "model.layers.41.input_layernorm.weight", - "src": "model.layers.21.input_layernorm.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.A_log", - "src": "model.layers.21.linear_attn.A_log", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.conv1d.weight", - "src": "model.layers.21.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.dt_bias", - "src": "model.layers.21.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.in_proj_a.weight", - "src": "model.layers.21.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.in_proj_b.weight", - "src": "model.layers.21.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.in_proj_qkv.weight", - "src": "model.layers.21.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.in_proj_z.weight", - "src": "model.layers.21.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.norm.weight", - "src": "model.layers.21.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.linear_attn.out_proj.weight", - "src": "model.layers.21.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.mlp.down_proj.weight", - "src": "model.layers.21.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.mlp.gate_proj.weight", - "src": "model.layers.21.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.mlp.up_proj.weight", - "src": "model.layers.21.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.41.post_attention_layernorm.weight", - "src": "model.layers.21.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 41, - 21, - false - ] - }, - { - "key": "model.layers.42.input_layernorm.weight", - "src": "model.layers.22.input_layernorm.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.A_log", - "src": "model.layers.22.linear_attn.A_log", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.conv1d.weight", - "src": "model.layers.22.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.dt_bias", - "src": "model.layers.22.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.in_proj_a.weight", - "src": "model.layers.22.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.in_proj_b.weight", - "src": "model.layers.22.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.in_proj_qkv.weight", - "src": "model.layers.22.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.in_proj_z.weight", - "src": "model.layers.22.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.norm.weight", - "src": "model.layers.22.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.linear_attn.out_proj.weight", - "src": "model.layers.22.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.mlp.down_proj.weight", - "src": "model.layers.22.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.mlp.gate_proj.weight", - "src": "model.layers.22.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.mlp.up_proj.weight", - "src": "model.layers.22.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.42.post_attention_layernorm.weight", - "src": "model.layers.22.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 42, - 22, - false - ] - }, - { - "key": "model.layers.43.input_layernorm.weight", - "src": "model.layers.23.input_layernorm.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.mlp.down_proj.weight", - "src": "model.layers.23.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.mlp.gate_proj.weight", - "src": "model.layers.23.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.mlp.up_proj.weight", - "src": "model.layers.23.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.post_attention_layernorm.weight", - "src": "model.layers.23.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.self_attn.k_norm.weight", - "src": "model.layers.23.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.self_attn.k_proj.weight", - "src": "model.layers.23.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.self_attn.o_proj.weight", - "src": "model.layers.23.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.self_attn.q_norm.weight", - "src": "model.layers.23.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.self_attn.q_proj.weight", - "src": "model.layers.23.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.43.self_attn.v_proj.weight", - "src": "model.layers.23.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 43, - 23, - false - ] - }, - { - "key": "model.layers.44.input_layernorm.weight", - "src": "model.layers.20.input_layernorm.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.A_log", - "src": "model.layers.20.linear_attn.A_log", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.conv1d.weight", - "src": "model.layers.20.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.dt_bias", - "src": "model.layers.20.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.in_proj_a.weight", - "src": "model.layers.20.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.in_proj_b.weight", - "src": "model.layers.20.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.in_proj_qkv.weight", - "src": "model.layers.20.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.in_proj_z.weight", - "src": "model.layers.20.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.norm.weight", - "src": "model.layers.20.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.linear_attn.out_proj.weight", - "src": "model.layers.20.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.mlp.down_proj.weight", - "src": "model.layers.20.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.mlp.gate_proj.weight", - "src": "model.layers.20.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.mlp.up_proj.weight", - "src": "model.layers.20.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.44.post_attention_layernorm.weight", - "src": "model.layers.20.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 44, - 20, - true - ] - }, - { - "key": "model.layers.45.input_layernorm.weight", - "src": "model.layers.21.input_layernorm.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.A_log", - "src": "model.layers.21.linear_attn.A_log", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.conv1d.weight", - "src": "model.layers.21.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.dt_bias", - "src": "model.layers.21.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.in_proj_a.weight", - "src": "model.layers.21.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.in_proj_b.weight", - "src": "model.layers.21.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.in_proj_qkv.weight", - "src": "model.layers.21.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.in_proj_z.weight", - "src": "model.layers.21.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.norm.weight", - "src": "model.layers.21.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.linear_attn.out_proj.weight", - "src": "model.layers.21.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.mlp.down_proj.weight", - "src": "model.layers.21.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.mlp.gate_proj.weight", - "src": "model.layers.21.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.mlp.up_proj.weight", - "src": "model.layers.21.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.45.post_attention_layernorm.weight", - "src": "model.layers.21.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 45, - 21, - true - ] - }, - { - "key": "model.layers.46.input_layernorm.weight", - "src": "model.layers.22.input_layernorm.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.A_log", - "src": "model.layers.22.linear_attn.A_log", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.conv1d.weight", - "src": "model.layers.22.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.dt_bias", - "src": "model.layers.22.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.in_proj_a.weight", - "src": "model.layers.22.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.in_proj_b.weight", - "src": "model.layers.22.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.in_proj_qkv.weight", - "src": "model.layers.22.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.in_proj_z.weight", - "src": "model.layers.22.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.norm.weight", - "src": "model.layers.22.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.linear_attn.out_proj.weight", - "src": "model.layers.22.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.mlp.down_proj.weight", - "src": "model.layers.22.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.mlp.gate_proj.weight", - "src": "model.layers.22.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.mlp.up_proj.weight", - "src": "model.layers.22.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.46.post_attention_layernorm.weight", - "src": "model.layers.22.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 46, - 22, - true - ] - }, - { - "key": "model.layers.47.input_layernorm.weight", - "src": "model.layers.23.input_layernorm.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.mlp.down_proj.weight", - "src": "model.layers.23.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.mlp.gate_proj.weight", - "src": "model.layers.23.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.mlp.up_proj.weight", - "src": "model.layers.23.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.post_attention_layernorm.weight", - "src": "model.layers.23.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.self_attn.k_norm.weight", - "src": "model.layers.23.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.self_attn.k_proj.weight", - "src": "model.layers.23.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.self_attn.o_proj.weight", - "src": "model.layers.23.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.self_attn.q_norm.weight", - "src": "model.layers.23.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.self_attn.q_proj.weight", - "src": "model.layers.23.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.47.self_attn.v_proj.weight", - "src": "model.layers.23.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 47, - 23, - true - ] - }, - { - "key": "model.layers.48.input_layernorm.weight", - "src": "model.layers.24.input_layernorm.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.A_log", - "src": "model.layers.24.linear_attn.A_log", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.conv1d.weight", - "src": "model.layers.24.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.dt_bias", - "src": "model.layers.24.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.in_proj_a.weight", - "src": "model.layers.24.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.in_proj_b.weight", - "src": "model.layers.24.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.in_proj_qkv.weight", - "src": "model.layers.24.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.in_proj_z.weight", - "src": "model.layers.24.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.norm.weight", - "src": "model.layers.24.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.linear_attn.out_proj.weight", - "src": "model.layers.24.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.mlp.down_proj.weight", - "src": "model.layers.24.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.mlp.gate_proj.weight", - "src": "model.layers.24.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.mlp.up_proj.weight", - "src": "model.layers.24.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.48.post_attention_layernorm.weight", - "src": "model.layers.24.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 48, - 24, - false - ] - }, - { - "key": "model.layers.49.input_layernorm.weight", - "src": "model.layers.25.input_layernorm.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.A_log", - "src": "model.layers.25.linear_attn.A_log", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.conv1d.weight", - "src": "model.layers.25.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.dt_bias", - "src": "model.layers.25.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.in_proj_a.weight", - "src": "model.layers.25.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.in_proj_b.weight", - "src": "model.layers.25.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.in_proj_qkv.weight", - "src": "model.layers.25.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.in_proj_z.weight", - "src": "model.layers.25.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.norm.weight", - "src": "model.layers.25.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.linear_attn.out_proj.weight", - "src": "model.layers.25.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.mlp.down_proj.weight", - "src": "model.layers.25.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.mlp.gate_proj.weight", - "src": "model.layers.25.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.mlp.up_proj.weight", - "src": "model.layers.25.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.49.post_attention_layernorm.weight", - "src": "model.layers.25.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 49, - 25, - false - ] - }, - { - "key": "model.layers.50.input_layernorm.weight", - "src": "model.layers.26.input_layernorm.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.A_log", - "src": "model.layers.26.linear_attn.A_log", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.conv1d.weight", - "src": "model.layers.26.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.dt_bias", - "src": "model.layers.26.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.in_proj_a.weight", - "src": "model.layers.26.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.in_proj_b.weight", - "src": "model.layers.26.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.in_proj_qkv.weight", - "src": "model.layers.26.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.in_proj_z.weight", - "src": "model.layers.26.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.norm.weight", - "src": "model.layers.26.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.linear_attn.out_proj.weight", - "src": "model.layers.26.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.mlp.down_proj.weight", - "src": "model.layers.26.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.mlp.gate_proj.weight", - "src": "model.layers.26.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.mlp.up_proj.weight", - "src": "model.layers.26.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.50.post_attention_layernorm.weight", - "src": "model.layers.26.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 50, - 26, - false - ] - }, - { - "key": "model.layers.51.input_layernorm.weight", - "src": "model.layers.27.input_layernorm.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.mlp.down_proj.weight", - "src": "model.layers.27.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.mlp.gate_proj.weight", - "src": "model.layers.27.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.mlp.up_proj.weight", - "src": "model.layers.27.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.post_attention_layernorm.weight", - "src": "model.layers.27.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.self_attn.k_norm.weight", - "src": "model.layers.27.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.self_attn.k_proj.weight", - "src": "model.layers.27.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.self_attn.o_proj.weight", - "src": "model.layers.27.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.self_attn.q_norm.weight", - "src": "model.layers.27.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.self_attn.q_proj.weight", - "src": "model.layers.27.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.51.self_attn.v_proj.weight", - "src": "model.layers.27.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 51, - 27, - false - ] - }, - { - "key": "model.layers.52.input_layernorm.weight", - "src": "model.layers.24.input_layernorm.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.A_log", - "src": "model.layers.24.linear_attn.A_log", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.conv1d.weight", - "src": "model.layers.24.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.dt_bias", - "src": "model.layers.24.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.in_proj_a.weight", - "src": "model.layers.24.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.in_proj_b.weight", - "src": "model.layers.24.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.in_proj_qkv.weight", - "src": "model.layers.24.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.in_proj_z.weight", - "src": "model.layers.24.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.norm.weight", - "src": "model.layers.24.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.linear_attn.out_proj.weight", - "src": "model.layers.24.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.mlp.down_proj.weight", - "src": "model.layers.24.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.mlp.gate_proj.weight", - "src": "model.layers.24.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.mlp.up_proj.weight", - "src": "model.layers.24.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.52.post_attention_layernorm.weight", - "src": "model.layers.24.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 52, - 24, - true - ] - }, - { - "key": "model.layers.53.input_layernorm.weight", - "src": "model.layers.25.input_layernorm.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.A_log", - "src": "model.layers.25.linear_attn.A_log", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.conv1d.weight", - "src": "model.layers.25.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.dt_bias", - "src": "model.layers.25.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.in_proj_a.weight", - "src": "model.layers.25.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.in_proj_b.weight", - "src": "model.layers.25.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.in_proj_qkv.weight", - "src": "model.layers.25.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.in_proj_z.weight", - "src": "model.layers.25.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.norm.weight", - "src": "model.layers.25.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.linear_attn.out_proj.weight", - "src": "model.layers.25.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.mlp.down_proj.weight", - "src": "model.layers.25.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.mlp.gate_proj.weight", - "src": "model.layers.25.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.mlp.up_proj.weight", - "src": "model.layers.25.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.53.post_attention_layernorm.weight", - "src": "model.layers.25.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 53, - 25, - true - ] - }, - { - "key": "model.layers.54.input_layernorm.weight", - "src": "model.layers.26.input_layernorm.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.A_log", - "src": "model.layers.26.linear_attn.A_log", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.conv1d.weight", - "src": "model.layers.26.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.dt_bias", - "src": "model.layers.26.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.in_proj_a.weight", - "src": "model.layers.26.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.in_proj_b.weight", - "src": "model.layers.26.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.in_proj_qkv.weight", - "src": "model.layers.26.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.in_proj_z.weight", - "src": "model.layers.26.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.norm.weight", - "src": "model.layers.26.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.linear_attn.out_proj.weight", - "src": "model.layers.26.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.mlp.down_proj.weight", - "src": "model.layers.26.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.mlp.gate_proj.weight", - "src": "model.layers.26.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.mlp.up_proj.weight", - "src": "model.layers.26.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.54.post_attention_layernorm.weight", - "src": "model.layers.26.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 54, - 26, - true - ] - }, - { - "key": "model.layers.55.input_layernorm.weight", - "src": "model.layers.27.input_layernorm.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.mlp.down_proj.weight", - "src": "model.layers.27.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.mlp.gate_proj.weight", - "src": "model.layers.27.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.mlp.up_proj.weight", - "src": "model.layers.27.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.post_attention_layernorm.weight", - "src": "model.layers.27.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.self_attn.k_norm.weight", - "src": "model.layers.27.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.self_attn.k_proj.weight", - "src": "model.layers.27.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.self_attn.o_proj.weight", - "src": "model.layers.27.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.self_attn.q_norm.weight", - "src": "model.layers.27.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.self_attn.q_proj.weight", - "src": "model.layers.27.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.55.self_attn.v_proj.weight", - "src": "model.layers.27.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 55, - 27, - true - ] - }, - { - "key": "model.layers.56.input_layernorm.weight", - "src": "model.layers.28.input_layernorm.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.A_log", - "src": "model.layers.28.linear_attn.A_log", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.conv1d.weight", - "src": "model.layers.28.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.dt_bias", - "src": "model.layers.28.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.in_proj_a.weight", - "src": "model.layers.28.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.in_proj_b.weight", - "src": "model.layers.28.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.in_proj_qkv.weight", - "src": "model.layers.28.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.in_proj_z.weight", - "src": "model.layers.28.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.norm.weight", - "src": "model.layers.28.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.linear_attn.out_proj.weight", - "src": "model.layers.28.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.mlp.down_proj.weight", - "src": "model.layers.28.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.mlp.gate_proj.weight", - "src": "model.layers.28.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.mlp.up_proj.weight", - "src": "model.layers.28.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.56.post_attention_layernorm.weight", - "src": "model.layers.28.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 56, - 28, - false - ] - }, - { - "key": "model.layers.57.input_layernorm.weight", - "src": "model.layers.29.input_layernorm.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.A_log", - "src": "model.layers.29.linear_attn.A_log", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.conv1d.weight", - "src": "model.layers.29.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.dt_bias", - "src": "model.layers.29.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.in_proj_a.weight", - "src": "model.layers.29.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.in_proj_b.weight", - "src": "model.layers.29.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.in_proj_qkv.weight", - "src": "model.layers.29.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.in_proj_z.weight", - "src": "model.layers.29.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.norm.weight", - "src": "model.layers.29.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.linear_attn.out_proj.weight", - "src": "model.layers.29.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.mlp.down_proj.weight", - "src": "model.layers.29.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.mlp.gate_proj.weight", - "src": "model.layers.29.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.mlp.up_proj.weight", - "src": "model.layers.29.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.57.post_attention_layernorm.weight", - "src": "model.layers.29.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 57, - 29, - false - ] - }, - { - "key": "model.layers.58.input_layernorm.weight", - "src": "model.layers.30.input_layernorm.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.A_log", - "src": "model.layers.30.linear_attn.A_log", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.conv1d.weight", - "src": "model.layers.30.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.dt_bias", - "src": "model.layers.30.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.in_proj_a.weight", - "src": "model.layers.30.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.in_proj_b.weight", - "src": "model.layers.30.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.in_proj_qkv.weight", - "src": "model.layers.30.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.in_proj_z.weight", - "src": "model.layers.30.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.norm.weight", - "src": "model.layers.30.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.linear_attn.out_proj.weight", - "src": "model.layers.30.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.mlp.down_proj.weight", - "src": "model.layers.30.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.mlp.gate_proj.weight", - "src": "model.layers.30.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.mlp.up_proj.weight", - "src": "model.layers.30.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.58.post_attention_layernorm.weight", - "src": "model.layers.30.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 58, - 30, - false - ] - }, - { - "key": "model.layers.59.input_layernorm.weight", - "src": "model.layers.31.input_layernorm.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.mlp.down_proj.weight", - "src": "model.layers.31.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.mlp.gate_proj.weight", - "src": "model.layers.31.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.mlp.up_proj.weight", - "src": "model.layers.31.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.post_attention_layernorm.weight", - "src": "model.layers.31.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.self_attn.k_norm.weight", - "src": "model.layers.31.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.self_attn.k_proj.weight", - "src": "model.layers.31.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.self_attn.o_proj.weight", - "src": "model.layers.31.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.self_attn.q_norm.weight", - "src": "model.layers.31.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.self_attn.q_proj.weight", - "src": "model.layers.31.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.59.self_attn.v_proj.weight", - "src": "model.layers.31.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 59, - 31, - false - ] - }, - { - "key": "model.layers.60.input_layernorm.weight", - "src": "model.layers.28.input_layernorm.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.A_log", - "src": "model.layers.28.linear_attn.A_log", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.conv1d.weight", - "src": "model.layers.28.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.dt_bias", - "src": "model.layers.28.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.in_proj_a.weight", - "src": "model.layers.28.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.in_proj_b.weight", - "src": "model.layers.28.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.in_proj_qkv.weight", - "src": "model.layers.28.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.in_proj_z.weight", - "src": "model.layers.28.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.norm.weight", - "src": "model.layers.28.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.linear_attn.out_proj.weight", - "src": "model.layers.28.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.mlp.down_proj.weight", - "src": "model.layers.28.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.mlp.gate_proj.weight", - "src": "model.layers.28.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.mlp.up_proj.weight", - "src": "model.layers.28.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.60.post_attention_layernorm.weight", - "src": "model.layers.28.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 60, - 28, - true - ] - }, - { - "key": "model.layers.61.input_layernorm.weight", - "src": "model.layers.29.input_layernorm.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.A_log", - "src": "model.layers.29.linear_attn.A_log", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.conv1d.weight", - "src": "model.layers.29.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.dt_bias", - "src": "model.layers.29.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.in_proj_a.weight", - "src": "model.layers.29.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.in_proj_b.weight", - "src": "model.layers.29.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.in_proj_qkv.weight", - "src": "model.layers.29.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.in_proj_z.weight", - "src": "model.layers.29.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.norm.weight", - "src": "model.layers.29.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.linear_attn.out_proj.weight", - "src": "model.layers.29.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.mlp.down_proj.weight", - "src": "model.layers.29.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.mlp.gate_proj.weight", - "src": "model.layers.29.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.mlp.up_proj.weight", - "src": "model.layers.29.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.61.post_attention_layernorm.weight", - "src": "model.layers.29.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 61, - 29, - true - ] - }, - { - "key": "model.layers.62.input_layernorm.weight", - "src": "model.layers.30.input_layernorm.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.A_log", - "src": "model.layers.30.linear_attn.A_log", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.conv1d.weight", - "src": "model.layers.30.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.dt_bias", - "src": "model.layers.30.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.in_proj_a.weight", - "src": "model.layers.30.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.in_proj_b.weight", - "src": "model.layers.30.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.in_proj_qkv.weight", - "src": "model.layers.30.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.in_proj_z.weight", - "src": "model.layers.30.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.norm.weight", - "src": "model.layers.30.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.linear_attn.out_proj.weight", - "src": "model.layers.30.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.mlp.down_proj.weight", - "src": "model.layers.30.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.mlp.gate_proj.weight", - "src": "model.layers.30.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.mlp.up_proj.weight", - "src": "model.layers.30.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.62.post_attention_layernorm.weight", - "src": "model.layers.30.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 62, - 30, - true - ] - }, - { - "key": "model.layers.63.input_layernorm.weight", - "src": "model.layers.31.input_layernorm.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.mlp.down_proj.weight", - "src": "model.layers.31.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.mlp.gate_proj.weight", - "src": "model.layers.31.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.mlp.up_proj.weight", - "src": "model.layers.31.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.post_attention_layernorm.weight", - "src": "model.layers.31.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.self_attn.k_norm.weight", - "src": "model.layers.31.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.self_attn.k_proj.weight", - "src": "model.layers.31.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.self_attn.o_proj.weight", - "src": "model.layers.31.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.self_attn.q_norm.weight", - "src": "model.layers.31.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.self_attn.q_proj.weight", - "src": "model.layers.31.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.63.self_attn.v_proj.weight", - "src": "model.layers.31.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 63, - 31, - true - ] - }, - { - "key": "model.layers.64.input_layernorm.weight", - "src": "model.layers.32.input_layernorm.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.A_log", - "src": "model.layers.32.linear_attn.A_log", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.conv1d.weight", - "src": "model.layers.32.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.dt_bias", - "src": "model.layers.32.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.in_proj_a.weight", - "src": "model.layers.32.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.in_proj_b.weight", - "src": "model.layers.32.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.in_proj_qkv.weight", - "src": "model.layers.32.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.in_proj_z.weight", - "src": "model.layers.32.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.norm.weight", - "src": "model.layers.32.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.linear_attn.out_proj.weight", - "src": "model.layers.32.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.mlp.down_proj.weight", - "src": "model.layers.32.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.mlp.gate_proj.weight", - "src": "model.layers.32.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.mlp.up_proj.weight", - "src": "model.layers.32.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.64.post_attention_layernorm.weight", - "src": "model.layers.32.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 64, - 32, - false - ] - }, - { - "key": "model.layers.65.input_layernorm.weight", - "src": "model.layers.33.input_layernorm.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.A_log", - "src": "model.layers.33.linear_attn.A_log", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.conv1d.weight", - "src": "model.layers.33.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.dt_bias", - "src": "model.layers.33.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.in_proj_a.weight", - "src": "model.layers.33.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.in_proj_b.weight", - "src": "model.layers.33.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.in_proj_qkv.weight", - "src": "model.layers.33.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.in_proj_z.weight", - "src": "model.layers.33.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.norm.weight", - "src": "model.layers.33.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.linear_attn.out_proj.weight", - "src": "model.layers.33.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.mlp.down_proj.weight", - "src": "model.layers.33.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.mlp.gate_proj.weight", - "src": "model.layers.33.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.mlp.up_proj.weight", - "src": "model.layers.33.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.65.post_attention_layernorm.weight", - "src": "model.layers.33.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 65, - 33, - false - ] - }, - { - "key": "model.layers.66.input_layernorm.weight", - "src": "model.layers.34.input_layernorm.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.A_log", - "src": "model.layers.34.linear_attn.A_log", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.conv1d.weight", - "src": "model.layers.34.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.dt_bias", - "src": "model.layers.34.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.in_proj_a.weight", - "src": "model.layers.34.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.in_proj_b.weight", - "src": "model.layers.34.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.in_proj_qkv.weight", - "src": "model.layers.34.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.in_proj_z.weight", - "src": "model.layers.34.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.norm.weight", - "src": "model.layers.34.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.linear_attn.out_proj.weight", - "src": "model.layers.34.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.mlp.down_proj.weight", - "src": "model.layers.34.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.mlp.gate_proj.weight", - "src": "model.layers.34.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.mlp.up_proj.weight", - "src": "model.layers.34.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.66.post_attention_layernorm.weight", - "src": "model.layers.34.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 66, - 34, - false - ] - }, - { - "key": "model.layers.67.input_layernorm.weight", - "src": "model.layers.35.input_layernorm.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.mlp.down_proj.weight", - "src": "model.layers.35.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.mlp.gate_proj.weight", - "src": "model.layers.35.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.mlp.up_proj.weight", - "src": "model.layers.35.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.post_attention_layernorm.weight", - "src": "model.layers.35.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.self_attn.k_norm.weight", - "src": "model.layers.35.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.self_attn.k_proj.weight", - "src": "model.layers.35.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.self_attn.o_proj.weight", - "src": "model.layers.35.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.self_attn.q_norm.weight", - "src": "model.layers.35.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.self_attn.q_proj.weight", - "src": "model.layers.35.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.67.self_attn.v_proj.weight", - "src": "model.layers.35.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 67, - 35, - false - ] - }, - { - "key": "model.layers.68.input_layernorm.weight", - "src": "model.layers.32.input_layernorm.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.A_log", - "src": "model.layers.32.linear_attn.A_log", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.conv1d.weight", - "src": "model.layers.32.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.dt_bias", - "src": "model.layers.32.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.in_proj_a.weight", - "src": "model.layers.32.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.in_proj_b.weight", - "src": "model.layers.32.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.in_proj_qkv.weight", - "src": "model.layers.32.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.in_proj_z.weight", - "src": "model.layers.32.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.norm.weight", - "src": "model.layers.32.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.linear_attn.out_proj.weight", - "src": "model.layers.32.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.mlp.down_proj.weight", - "src": "model.layers.32.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.mlp.gate_proj.weight", - "src": "model.layers.32.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.mlp.up_proj.weight", - "src": "model.layers.32.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.68.post_attention_layernorm.weight", - "src": "model.layers.32.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 68, - 32, - true - ] - }, - { - "key": "model.layers.69.input_layernorm.weight", - "src": "model.layers.33.input_layernorm.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.A_log", - "src": "model.layers.33.linear_attn.A_log", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.conv1d.weight", - "src": "model.layers.33.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.dt_bias", - "src": "model.layers.33.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.in_proj_a.weight", - "src": "model.layers.33.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.in_proj_b.weight", - "src": "model.layers.33.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.in_proj_qkv.weight", - "src": "model.layers.33.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.in_proj_z.weight", - "src": "model.layers.33.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.norm.weight", - "src": "model.layers.33.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.linear_attn.out_proj.weight", - "src": "model.layers.33.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.mlp.down_proj.weight", - "src": "model.layers.33.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.mlp.gate_proj.weight", - "src": "model.layers.33.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.mlp.up_proj.weight", - "src": "model.layers.33.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.69.post_attention_layernorm.weight", - "src": "model.layers.33.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 69, - 33, - true - ] - }, - { - "key": "model.layers.70.input_layernorm.weight", - "src": "model.layers.34.input_layernorm.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.A_log", - "src": "model.layers.34.linear_attn.A_log", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.conv1d.weight", - "src": "model.layers.34.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.dt_bias", - "src": "model.layers.34.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.in_proj_a.weight", - "src": "model.layers.34.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.in_proj_b.weight", - "src": "model.layers.34.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.in_proj_qkv.weight", - "src": "model.layers.34.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.in_proj_z.weight", - "src": "model.layers.34.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.norm.weight", - "src": "model.layers.34.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.linear_attn.out_proj.weight", - "src": "model.layers.34.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.mlp.down_proj.weight", - "src": "model.layers.34.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.mlp.gate_proj.weight", - "src": "model.layers.34.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.mlp.up_proj.weight", - "src": "model.layers.34.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.70.post_attention_layernorm.weight", - "src": "model.layers.34.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 70, - 34, - true - ] - }, - { - "key": "model.layers.71.input_layernorm.weight", - "src": "model.layers.35.input_layernorm.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.mlp.down_proj.weight", - "src": "model.layers.35.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.mlp.gate_proj.weight", - "src": "model.layers.35.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.mlp.up_proj.weight", - "src": "model.layers.35.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.post_attention_layernorm.weight", - "src": "model.layers.35.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.self_attn.k_norm.weight", - "src": "model.layers.35.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.self_attn.k_proj.weight", - "src": "model.layers.35.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.self_attn.o_proj.weight", - "src": "model.layers.35.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.self_attn.q_norm.weight", - "src": "model.layers.35.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.self_attn.q_proj.weight", - "src": "model.layers.35.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.71.self_attn.v_proj.weight", - "src": "model.layers.35.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 71, - 35, - true - ] - }, - { - "key": "model.layers.72.input_layernorm.weight", - "src": "model.layers.36.input_layernorm.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.A_log", - "src": "model.layers.36.linear_attn.A_log", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.conv1d.weight", - "src": "model.layers.36.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.dt_bias", - "src": "model.layers.36.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.in_proj_a.weight", - "src": "model.layers.36.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.in_proj_b.weight", - "src": "model.layers.36.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.in_proj_qkv.weight", - "src": "model.layers.36.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.in_proj_z.weight", - "src": "model.layers.36.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.norm.weight", - "src": "model.layers.36.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.linear_attn.out_proj.weight", - "src": "model.layers.36.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.mlp.down_proj.weight", - "src": "model.layers.36.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.mlp.gate_proj.weight", - "src": "model.layers.36.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.mlp.up_proj.weight", - "src": "model.layers.36.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.72.post_attention_layernorm.weight", - "src": "model.layers.36.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 72, - 36, - false - ] - }, - { - "key": "model.layers.73.input_layernorm.weight", - "src": "model.layers.37.input_layernorm.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.A_log", - "src": "model.layers.37.linear_attn.A_log", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.conv1d.weight", - "src": "model.layers.37.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.dt_bias", - "src": "model.layers.37.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.in_proj_a.weight", - "src": "model.layers.37.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.in_proj_b.weight", - "src": "model.layers.37.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.in_proj_qkv.weight", - "src": "model.layers.37.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.in_proj_z.weight", - "src": "model.layers.37.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.norm.weight", - "src": "model.layers.37.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.linear_attn.out_proj.weight", - "src": "model.layers.37.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.mlp.down_proj.weight", - "src": "model.layers.37.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.mlp.gate_proj.weight", - "src": "model.layers.37.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.mlp.up_proj.weight", - "src": "model.layers.37.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.73.post_attention_layernorm.weight", - "src": "model.layers.37.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 73, - 37, - false - ] - }, - { - "key": "model.layers.74.input_layernorm.weight", - "src": "model.layers.38.input_layernorm.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.A_log", - "src": "model.layers.38.linear_attn.A_log", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.conv1d.weight", - "src": "model.layers.38.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.dt_bias", - "src": "model.layers.38.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.in_proj_a.weight", - "src": "model.layers.38.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.in_proj_b.weight", - "src": "model.layers.38.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.in_proj_qkv.weight", - "src": "model.layers.38.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.in_proj_z.weight", - "src": "model.layers.38.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.norm.weight", - "src": "model.layers.38.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.linear_attn.out_proj.weight", - "src": "model.layers.38.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.mlp.down_proj.weight", - "src": "model.layers.38.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.mlp.gate_proj.weight", - "src": "model.layers.38.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.mlp.up_proj.weight", - "src": "model.layers.38.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.74.post_attention_layernorm.weight", - "src": "model.layers.38.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 74, - 38, - false - ] - }, - { - "key": "model.layers.75.input_layernorm.weight", - "src": "model.layers.39.input_layernorm.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.mlp.down_proj.weight", - "src": "model.layers.39.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.mlp.gate_proj.weight", - "src": "model.layers.39.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.mlp.up_proj.weight", - "src": "model.layers.39.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.post_attention_layernorm.weight", - "src": "model.layers.39.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.self_attn.k_norm.weight", - "src": "model.layers.39.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.self_attn.k_proj.weight", - "src": "model.layers.39.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.self_attn.o_proj.weight", - "src": "model.layers.39.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.self_attn.q_norm.weight", - "src": "model.layers.39.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.self_attn.q_proj.weight", - "src": "model.layers.39.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.75.self_attn.v_proj.weight", - "src": "model.layers.39.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 75, - 39, - false - ] - }, - { - "key": "model.layers.76.input_layernorm.weight", - "src": "model.layers.36.input_layernorm.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.A_log", - "src": "model.layers.36.linear_attn.A_log", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.conv1d.weight", - "src": "model.layers.36.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.dt_bias", - "src": "model.layers.36.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.in_proj_a.weight", - "src": "model.layers.36.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.in_proj_b.weight", - "src": "model.layers.36.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.in_proj_qkv.weight", - "src": "model.layers.36.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.in_proj_z.weight", - "src": "model.layers.36.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.norm.weight", - "src": "model.layers.36.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.linear_attn.out_proj.weight", - "src": "model.layers.36.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.mlp.down_proj.weight", - "src": "model.layers.36.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.mlp.gate_proj.weight", - "src": "model.layers.36.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.mlp.up_proj.weight", - "src": "model.layers.36.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.76.post_attention_layernorm.weight", - "src": "model.layers.36.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 76, - 36, - true - ] - }, - { - "key": "model.layers.77.input_layernorm.weight", - "src": "model.layers.37.input_layernorm.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.A_log", - "src": "model.layers.37.linear_attn.A_log", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.conv1d.weight", - "src": "model.layers.37.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.dt_bias", - "src": "model.layers.37.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.in_proj_a.weight", - "src": "model.layers.37.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.in_proj_b.weight", - "src": "model.layers.37.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.in_proj_qkv.weight", - "src": "model.layers.37.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.in_proj_z.weight", - "src": "model.layers.37.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.norm.weight", - "src": "model.layers.37.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.linear_attn.out_proj.weight", - "src": "model.layers.37.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.mlp.down_proj.weight", - "src": "model.layers.37.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.mlp.gate_proj.weight", - "src": "model.layers.37.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.mlp.up_proj.weight", - "src": "model.layers.37.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.77.post_attention_layernorm.weight", - "src": "model.layers.37.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 77, - 37, - true - ] - }, - { - "key": "model.layers.78.input_layernorm.weight", - "src": "model.layers.38.input_layernorm.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.A_log", - "src": "model.layers.38.linear_attn.A_log", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.conv1d.weight", - "src": "model.layers.38.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.dt_bias", - "src": "model.layers.38.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.in_proj_a.weight", - "src": "model.layers.38.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.in_proj_b.weight", - "src": "model.layers.38.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.in_proj_qkv.weight", - "src": "model.layers.38.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.in_proj_z.weight", - "src": "model.layers.38.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.norm.weight", - "src": "model.layers.38.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.linear_attn.out_proj.weight", - "src": "model.layers.38.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.mlp.down_proj.weight", - "src": "model.layers.38.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.mlp.gate_proj.weight", - "src": "model.layers.38.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.mlp.up_proj.weight", - "src": "model.layers.38.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.78.post_attention_layernorm.weight", - "src": "model.layers.38.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 78, - 38, - true - ] - }, - { - "key": "model.layers.79.input_layernorm.weight", - "src": "model.layers.39.input_layernorm.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.mlp.down_proj.weight", - "src": "model.layers.39.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.mlp.gate_proj.weight", - "src": "model.layers.39.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.mlp.up_proj.weight", - "src": "model.layers.39.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.post_attention_layernorm.weight", - "src": "model.layers.39.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.self_attn.k_norm.weight", - "src": "model.layers.39.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.self_attn.k_proj.weight", - "src": "model.layers.39.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.self_attn.o_proj.weight", - "src": "model.layers.39.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.self_attn.q_norm.weight", - "src": "model.layers.39.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.self_attn.q_proj.weight", - "src": "model.layers.39.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.79.self_attn.v_proj.weight", - "src": "model.layers.39.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 79, - 39, - true - ] - }, - { - "key": "model.layers.80.input_layernorm.weight", - "src": "model.layers.40.input_layernorm.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.A_log", - "src": "model.layers.40.linear_attn.A_log", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.conv1d.weight", - "src": "model.layers.40.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.dt_bias", - "src": "model.layers.40.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.in_proj_a.weight", - "src": "model.layers.40.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.in_proj_b.weight", - "src": "model.layers.40.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.in_proj_qkv.weight", - "src": "model.layers.40.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.in_proj_z.weight", - "src": "model.layers.40.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.norm.weight", - "src": "model.layers.40.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.linear_attn.out_proj.weight", - "src": "model.layers.40.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.mlp.down_proj.weight", - "src": "model.layers.40.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.mlp.gate_proj.weight", - "src": "model.layers.40.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.mlp.up_proj.weight", - "src": "model.layers.40.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.80.post_attention_layernorm.weight", - "src": "model.layers.40.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 80, - 40, - false - ] - }, - { - "key": "model.layers.81.input_layernorm.weight", - "src": "model.layers.41.input_layernorm.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.A_log", - "src": "model.layers.41.linear_attn.A_log", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.conv1d.weight", - "src": "model.layers.41.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.dt_bias", - "src": "model.layers.41.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.in_proj_a.weight", - "src": "model.layers.41.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.in_proj_b.weight", - "src": "model.layers.41.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.in_proj_qkv.weight", - "src": "model.layers.41.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.in_proj_z.weight", - "src": "model.layers.41.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.norm.weight", - "src": "model.layers.41.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.linear_attn.out_proj.weight", - "src": "model.layers.41.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.mlp.down_proj.weight", - "src": "model.layers.41.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.mlp.gate_proj.weight", - "src": "model.layers.41.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.mlp.up_proj.weight", - "src": "model.layers.41.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.81.post_attention_layernorm.weight", - "src": "model.layers.41.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 81, - 41, - false - ] - }, - { - "key": "model.layers.82.input_layernorm.weight", - "src": "model.layers.42.input_layernorm.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.A_log", - "src": "model.layers.42.linear_attn.A_log", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.conv1d.weight", - "src": "model.layers.42.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.dt_bias", - "src": "model.layers.42.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.in_proj_a.weight", - "src": "model.layers.42.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.in_proj_b.weight", - "src": "model.layers.42.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.in_proj_qkv.weight", - "src": "model.layers.42.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.in_proj_z.weight", - "src": "model.layers.42.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.norm.weight", - "src": "model.layers.42.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.linear_attn.out_proj.weight", - "src": "model.layers.42.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.mlp.down_proj.weight", - "src": "model.layers.42.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.mlp.gate_proj.weight", - "src": "model.layers.42.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.mlp.up_proj.weight", - "src": "model.layers.42.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.82.post_attention_layernorm.weight", - "src": "model.layers.42.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 82, - 42, - false - ] - }, - { - "key": "model.layers.83.input_layernorm.weight", - "src": "model.layers.43.input_layernorm.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.mlp.down_proj.weight", - "src": "model.layers.43.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.mlp.gate_proj.weight", - "src": "model.layers.43.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.mlp.up_proj.weight", - "src": "model.layers.43.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.post_attention_layernorm.weight", - "src": "model.layers.43.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.self_attn.k_norm.weight", - "src": "model.layers.43.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.self_attn.k_proj.weight", - "src": "model.layers.43.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.self_attn.o_proj.weight", - "src": "model.layers.43.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.self_attn.q_norm.weight", - "src": "model.layers.43.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.self_attn.q_proj.weight", - "src": "model.layers.43.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.83.self_attn.v_proj.weight", - "src": "model.layers.43.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 83, - 43, - false - ] - }, - { - "key": "model.layers.84.input_layernorm.weight", - "src": "model.layers.40.input_layernorm.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.A_log", - "src": "model.layers.40.linear_attn.A_log", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.conv1d.weight", - "src": "model.layers.40.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.dt_bias", - "src": "model.layers.40.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.in_proj_a.weight", - "src": "model.layers.40.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.in_proj_b.weight", - "src": "model.layers.40.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.in_proj_qkv.weight", - "src": "model.layers.40.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.in_proj_z.weight", - "src": "model.layers.40.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.norm.weight", - "src": "model.layers.40.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.linear_attn.out_proj.weight", - "src": "model.layers.40.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.mlp.down_proj.weight", - "src": "model.layers.40.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.mlp.gate_proj.weight", - "src": "model.layers.40.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.mlp.up_proj.weight", - "src": "model.layers.40.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.84.post_attention_layernorm.weight", - "src": "model.layers.40.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 84, - 40, - true - ] - }, - { - "key": "model.layers.85.input_layernorm.weight", - "src": "model.layers.41.input_layernorm.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.A_log", - "src": "model.layers.41.linear_attn.A_log", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.conv1d.weight", - "src": "model.layers.41.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.dt_bias", - "src": "model.layers.41.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.in_proj_a.weight", - "src": "model.layers.41.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.in_proj_b.weight", - "src": "model.layers.41.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.in_proj_qkv.weight", - "src": "model.layers.41.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.in_proj_z.weight", - "src": "model.layers.41.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.norm.weight", - "src": "model.layers.41.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.linear_attn.out_proj.weight", - "src": "model.layers.41.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.mlp.down_proj.weight", - "src": "model.layers.41.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.mlp.gate_proj.weight", - "src": "model.layers.41.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.mlp.up_proj.weight", - "src": "model.layers.41.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.85.post_attention_layernorm.weight", - "src": "model.layers.41.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 85, - 41, - true - ] - }, - { - "key": "model.layers.86.input_layernorm.weight", - "src": "model.layers.42.input_layernorm.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.A_log", - "src": "model.layers.42.linear_attn.A_log", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.conv1d.weight", - "src": "model.layers.42.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.dt_bias", - "src": "model.layers.42.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.in_proj_a.weight", - "src": "model.layers.42.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.in_proj_b.weight", - "src": "model.layers.42.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.in_proj_qkv.weight", - "src": "model.layers.42.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.in_proj_z.weight", - "src": "model.layers.42.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.norm.weight", - "src": "model.layers.42.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.linear_attn.out_proj.weight", - "src": "model.layers.42.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.mlp.down_proj.weight", - "src": "model.layers.42.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.mlp.gate_proj.weight", - "src": "model.layers.42.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.mlp.up_proj.weight", - "src": "model.layers.42.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.86.post_attention_layernorm.weight", - "src": "model.layers.42.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 86, - 42, - true - ] - }, - { - "key": "model.layers.87.input_layernorm.weight", - "src": "model.layers.43.input_layernorm.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.mlp.down_proj.weight", - "src": "model.layers.43.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.mlp.gate_proj.weight", - "src": "model.layers.43.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.mlp.up_proj.weight", - "src": "model.layers.43.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.post_attention_layernorm.weight", - "src": "model.layers.43.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.self_attn.k_norm.weight", - "src": "model.layers.43.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.self_attn.k_proj.weight", - "src": "model.layers.43.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.self_attn.o_proj.weight", - "src": "model.layers.43.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.self_attn.q_norm.weight", - "src": "model.layers.43.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.self_attn.q_proj.weight", - "src": "model.layers.43.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.87.self_attn.v_proj.weight", - "src": "model.layers.43.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 87, - 43, - true - ] - }, - { - "key": "model.layers.88.input_layernorm.weight", - "src": "model.layers.44.input_layernorm.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.A_log", - "src": "model.layers.44.linear_attn.A_log", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.conv1d.weight", - "src": "model.layers.44.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.dt_bias", - "src": "model.layers.44.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.in_proj_a.weight", - "src": "model.layers.44.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.in_proj_b.weight", - "src": "model.layers.44.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.in_proj_qkv.weight", - "src": "model.layers.44.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.in_proj_z.weight", - "src": "model.layers.44.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.norm.weight", - "src": "model.layers.44.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.linear_attn.out_proj.weight", - "src": "model.layers.44.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.mlp.down_proj.weight", - "src": "model.layers.44.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.mlp.gate_proj.weight", - "src": "model.layers.44.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.mlp.up_proj.weight", - "src": "model.layers.44.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.88.post_attention_layernorm.weight", - "src": "model.layers.44.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 88, - 44, - false - ] - }, - { - "key": "model.layers.89.input_layernorm.weight", - "src": "model.layers.45.input_layernorm.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.A_log", - "src": "model.layers.45.linear_attn.A_log", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.conv1d.weight", - "src": "model.layers.45.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.dt_bias", - "src": "model.layers.45.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.in_proj_a.weight", - "src": "model.layers.45.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.in_proj_b.weight", - "src": "model.layers.45.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.in_proj_qkv.weight", - "src": "model.layers.45.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.in_proj_z.weight", - "src": "model.layers.45.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.norm.weight", - "src": "model.layers.45.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.linear_attn.out_proj.weight", - "src": "model.layers.45.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.mlp.down_proj.weight", - "src": "model.layers.45.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.mlp.gate_proj.weight", - "src": "model.layers.45.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.mlp.up_proj.weight", - "src": "model.layers.45.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.89.post_attention_layernorm.weight", - "src": "model.layers.45.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 89, - 45, - false - ] - }, - { - "key": "model.layers.90.input_layernorm.weight", - "src": "model.layers.46.input_layernorm.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.A_log", - "src": "model.layers.46.linear_attn.A_log", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.conv1d.weight", - "src": "model.layers.46.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.dt_bias", - "src": "model.layers.46.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.in_proj_a.weight", - "src": "model.layers.46.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.in_proj_b.weight", - "src": "model.layers.46.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.in_proj_qkv.weight", - "src": "model.layers.46.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.in_proj_z.weight", - "src": "model.layers.46.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.norm.weight", - "src": "model.layers.46.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.linear_attn.out_proj.weight", - "src": "model.layers.46.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.mlp.down_proj.weight", - "src": "model.layers.46.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.mlp.gate_proj.weight", - "src": "model.layers.46.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.mlp.up_proj.weight", - "src": "model.layers.46.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.90.post_attention_layernorm.weight", - "src": "model.layers.46.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 90, - 46, - false - ] - }, - { - "key": "model.layers.91.input_layernorm.weight", - "src": "model.layers.47.input_layernorm.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.mlp.down_proj.weight", - "src": "model.layers.47.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.mlp.gate_proj.weight", - "src": "model.layers.47.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.mlp.up_proj.weight", - "src": "model.layers.47.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.post_attention_layernorm.weight", - "src": "model.layers.47.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.self_attn.k_norm.weight", - "src": "model.layers.47.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.self_attn.k_proj.weight", - "src": "model.layers.47.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.self_attn.o_proj.weight", - "src": "model.layers.47.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.self_attn.q_norm.weight", - "src": "model.layers.47.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.self_attn.q_proj.weight", - "src": "model.layers.47.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.91.self_attn.v_proj.weight", - "src": "model.layers.47.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 91, - 47, - false - ] - }, - { - "key": "model.layers.92.input_layernorm.weight", - "src": "model.layers.44.input_layernorm.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.A_log", - "src": "model.layers.44.linear_attn.A_log", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.conv1d.weight", - "src": "model.layers.44.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.dt_bias", - "src": "model.layers.44.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.in_proj_a.weight", - "src": "model.layers.44.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.in_proj_b.weight", - "src": "model.layers.44.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.in_proj_qkv.weight", - "src": "model.layers.44.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.in_proj_z.weight", - "src": "model.layers.44.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.norm.weight", - "src": "model.layers.44.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.linear_attn.out_proj.weight", - "src": "model.layers.44.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.mlp.down_proj.weight", - "src": "model.layers.44.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.mlp.gate_proj.weight", - "src": "model.layers.44.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.mlp.up_proj.weight", - "src": "model.layers.44.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.92.post_attention_layernorm.weight", - "src": "model.layers.44.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 92, - 44, - true - ] - }, - { - "key": "model.layers.93.input_layernorm.weight", - "src": "model.layers.45.input_layernorm.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.A_log", - "src": "model.layers.45.linear_attn.A_log", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.conv1d.weight", - "src": "model.layers.45.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.dt_bias", - "src": "model.layers.45.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.in_proj_a.weight", - "src": "model.layers.45.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.in_proj_b.weight", - "src": "model.layers.45.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.in_proj_qkv.weight", - "src": "model.layers.45.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.in_proj_z.weight", - "src": "model.layers.45.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.norm.weight", - "src": "model.layers.45.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.linear_attn.out_proj.weight", - "src": "model.layers.45.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.mlp.down_proj.weight", - "src": "model.layers.45.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.mlp.gate_proj.weight", - "src": "model.layers.45.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.mlp.up_proj.weight", - "src": "model.layers.45.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.93.post_attention_layernorm.weight", - "src": "model.layers.45.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 93, - 45, - true - ] - }, - { - "key": "model.layers.94.input_layernorm.weight", - "src": "model.layers.46.input_layernorm.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.A_log", - "src": "model.layers.46.linear_attn.A_log", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.conv1d.weight", - "src": "model.layers.46.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.dt_bias", - "src": "model.layers.46.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.in_proj_a.weight", - "src": "model.layers.46.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.in_proj_b.weight", - "src": "model.layers.46.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.in_proj_qkv.weight", - "src": "model.layers.46.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.in_proj_z.weight", - "src": "model.layers.46.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.norm.weight", - "src": "model.layers.46.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.linear_attn.out_proj.weight", - "src": "model.layers.46.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.mlp.down_proj.weight", - "src": "model.layers.46.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.mlp.gate_proj.weight", - "src": "model.layers.46.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.mlp.up_proj.weight", - "src": "model.layers.46.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.94.post_attention_layernorm.weight", - "src": "model.layers.46.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 94, - 46, - true - ] - }, - { - "key": "model.layers.95.input_layernorm.weight", - "src": "model.layers.47.input_layernorm.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.mlp.down_proj.weight", - "src": "model.layers.47.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.mlp.gate_proj.weight", - "src": "model.layers.47.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.mlp.up_proj.weight", - "src": "model.layers.47.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.post_attention_layernorm.weight", - "src": "model.layers.47.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.self_attn.k_norm.weight", - "src": "model.layers.47.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.self_attn.k_proj.weight", - "src": "model.layers.47.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.self_attn.o_proj.weight", - "src": "model.layers.47.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.self_attn.q_norm.weight", - "src": "model.layers.47.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.self_attn.q_proj.weight", - "src": "model.layers.47.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.95.self_attn.v_proj.weight", - "src": "model.layers.47.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 95, - 47, - true - ] - }, - { - "key": "model.layers.96.input_layernorm.weight", - "src": "model.layers.48.input_layernorm.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.A_log", - "src": "model.layers.48.linear_attn.A_log", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.conv1d.weight", - "src": "model.layers.48.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.dt_bias", - "src": "model.layers.48.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.in_proj_a.weight", - "src": "model.layers.48.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.in_proj_b.weight", - "src": "model.layers.48.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.in_proj_qkv.weight", - "src": "model.layers.48.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.in_proj_z.weight", - "src": "model.layers.48.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.norm.weight", - "src": "model.layers.48.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.linear_attn.out_proj.weight", - "src": "model.layers.48.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.mlp.down_proj.weight", - "src": "model.layers.48.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.mlp.gate_proj.weight", - "src": "model.layers.48.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.mlp.up_proj.weight", - "src": "model.layers.48.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.96.post_attention_layernorm.weight", - "src": "model.layers.48.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 96, - 48, - false - ] - }, - { - "key": "model.layers.97.input_layernorm.weight", - "src": "model.layers.49.input_layernorm.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.A_log", - "src": "model.layers.49.linear_attn.A_log", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.conv1d.weight", - "src": "model.layers.49.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.dt_bias", - "src": "model.layers.49.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.in_proj_a.weight", - "src": "model.layers.49.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.in_proj_b.weight", - "src": "model.layers.49.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.in_proj_qkv.weight", - "src": "model.layers.49.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.in_proj_z.weight", - "src": "model.layers.49.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.norm.weight", - "src": "model.layers.49.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.linear_attn.out_proj.weight", - "src": "model.layers.49.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.mlp.down_proj.weight", - "src": "model.layers.49.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.mlp.gate_proj.weight", - "src": "model.layers.49.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.mlp.up_proj.weight", - "src": "model.layers.49.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.97.post_attention_layernorm.weight", - "src": "model.layers.49.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 97, - 49, - false - ] - }, - { - "key": "model.layers.98.input_layernorm.weight", - "src": "model.layers.50.input_layernorm.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.A_log", - "src": "model.layers.50.linear_attn.A_log", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.conv1d.weight", - "src": "model.layers.50.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.dt_bias", - "src": "model.layers.50.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.in_proj_a.weight", - "src": "model.layers.50.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.in_proj_b.weight", - "src": "model.layers.50.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.in_proj_qkv.weight", - "src": "model.layers.50.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.in_proj_z.weight", - "src": "model.layers.50.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.norm.weight", - "src": "model.layers.50.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.linear_attn.out_proj.weight", - "src": "model.layers.50.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.mlp.down_proj.weight", - "src": "model.layers.50.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.mlp.gate_proj.weight", - "src": "model.layers.50.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.mlp.up_proj.weight", - "src": "model.layers.50.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.98.post_attention_layernorm.weight", - "src": "model.layers.50.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 98, - 50, - false - ] - }, - { - "key": "model.layers.99.input_layernorm.weight", - "src": "model.layers.51.input_layernorm.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.mlp.down_proj.weight", - "src": "model.layers.51.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.mlp.gate_proj.weight", - "src": "model.layers.51.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.mlp.up_proj.weight", - "src": "model.layers.51.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.post_attention_layernorm.weight", - "src": "model.layers.51.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.self_attn.k_norm.weight", - "src": "model.layers.51.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.self_attn.k_proj.weight", - "src": "model.layers.51.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.self_attn.o_proj.weight", - "src": "model.layers.51.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.self_attn.q_norm.weight", - "src": "model.layers.51.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.self_attn.q_proj.weight", - "src": "model.layers.51.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.99.self_attn.v_proj.weight", - "src": "model.layers.51.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 99, - 51, - false - ] - }, - { - "key": "model.layers.100.input_layernorm.weight", - "src": "model.layers.48.input_layernorm.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.A_log", - "src": "model.layers.48.linear_attn.A_log", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.conv1d.weight", - "src": "model.layers.48.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.dt_bias", - "src": "model.layers.48.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.in_proj_a.weight", - "src": "model.layers.48.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.in_proj_b.weight", - "src": "model.layers.48.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.in_proj_qkv.weight", - "src": "model.layers.48.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.in_proj_z.weight", - "src": "model.layers.48.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.norm.weight", - "src": "model.layers.48.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.linear_attn.out_proj.weight", - "src": "model.layers.48.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.mlp.down_proj.weight", - "src": "model.layers.48.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.mlp.gate_proj.weight", - "src": "model.layers.48.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.mlp.up_proj.weight", - "src": "model.layers.48.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.100.post_attention_layernorm.weight", - "src": "model.layers.48.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 100, - 48, - true - ] - }, - { - "key": "model.layers.101.input_layernorm.weight", - "src": "model.layers.49.input_layernorm.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.A_log", - "src": "model.layers.49.linear_attn.A_log", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.conv1d.weight", - "src": "model.layers.49.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.dt_bias", - "src": "model.layers.49.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.in_proj_a.weight", - "src": "model.layers.49.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.in_proj_b.weight", - "src": "model.layers.49.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.in_proj_qkv.weight", - "src": "model.layers.49.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.in_proj_z.weight", - "src": "model.layers.49.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.norm.weight", - "src": "model.layers.49.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.linear_attn.out_proj.weight", - "src": "model.layers.49.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.mlp.down_proj.weight", - "src": "model.layers.49.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.mlp.gate_proj.weight", - "src": "model.layers.49.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.mlp.up_proj.weight", - "src": "model.layers.49.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.101.post_attention_layernorm.weight", - "src": "model.layers.49.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 101, - 49, - true - ] - }, - { - "key": "model.layers.102.input_layernorm.weight", - "src": "model.layers.50.input_layernorm.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.A_log", - "src": "model.layers.50.linear_attn.A_log", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.conv1d.weight", - "src": "model.layers.50.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.dt_bias", - "src": "model.layers.50.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.in_proj_a.weight", - "src": "model.layers.50.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.in_proj_b.weight", - "src": "model.layers.50.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.in_proj_qkv.weight", - "src": "model.layers.50.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.in_proj_z.weight", - "src": "model.layers.50.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.norm.weight", - "src": "model.layers.50.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.linear_attn.out_proj.weight", - "src": "model.layers.50.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.mlp.down_proj.weight", - "src": "model.layers.50.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.mlp.gate_proj.weight", - "src": "model.layers.50.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.mlp.up_proj.weight", - "src": "model.layers.50.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.102.post_attention_layernorm.weight", - "src": "model.layers.50.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 102, - 50, - true - ] - }, - { - "key": "model.layers.103.input_layernorm.weight", - "src": "model.layers.51.input_layernorm.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.mlp.down_proj.weight", - "src": "model.layers.51.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.mlp.gate_proj.weight", - "src": "model.layers.51.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.mlp.up_proj.weight", - "src": "model.layers.51.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.post_attention_layernorm.weight", - "src": "model.layers.51.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.self_attn.k_norm.weight", - "src": "model.layers.51.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.self_attn.k_proj.weight", - "src": "model.layers.51.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.self_attn.o_proj.weight", - "src": "model.layers.51.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.self_attn.q_norm.weight", - "src": "model.layers.51.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.self_attn.q_proj.weight", - "src": "model.layers.51.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.103.self_attn.v_proj.weight", - "src": "model.layers.51.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 103, - 51, - true - ] - }, - { - "key": "model.layers.104.input_layernorm.weight", - "src": "model.layers.52.input_layernorm.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.A_log", - "src": "model.layers.52.linear_attn.A_log", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.conv1d.weight", - "src": "model.layers.52.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.dt_bias", - "src": "model.layers.52.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.in_proj_a.weight", - "src": "model.layers.52.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.in_proj_b.weight", - "src": "model.layers.52.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.in_proj_qkv.weight", - "src": "model.layers.52.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.in_proj_z.weight", - "src": "model.layers.52.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.norm.weight", - "src": "model.layers.52.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.linear_attn.out_proj.weight", - "src": "model.layers.52.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.mlp.down_proj.weight", - "src": "model.layers.52.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.mlp.gate_proj.weight", - "src": "model.layers.52.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.mlp.up_proj.weight", - "src": "model.layers.52.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.104.post_attention_layernorm.weight", - "src": "model.layers.52.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 104, - 52, - false - ] - }, - { - "key": "model.layers.105.input_layernorm.weight", - "src": "model.layers.53.input_layernorm.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.A_log", - "src": "model.layers.53.linear_attn.A_log", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.conv1d.weight", - "src": "model.layers.53.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.dt_bias", - "src": "model.layers.53.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.in_proj_a.weight", - "src": "model.layers.53.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.in_proj_b.weight", - "src": "model.layers.53.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.in_proj_qkv.weight", - "src": "model.layers.53.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.in_proj_z.weight", - "src": "model.layers.53.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.norm.weight", - "src": "model.layers.53.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.linear_attn.out_proj.weight", - "src": "model.layers.53.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.mlp.down_proj.weight", - "src": "model.layers.53.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.mlp.gate_proj.weight", - "src": "model.layers.53.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.mlp.up_proj.weight", - "src": "model.layers.53.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.105.post_attention_layernorm.weight", - "src": "model.layers.53.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 105, - 53, - false - ] - }, - { - "key": "model.layers.106.input_layernorm.weight", - "src": "model.layers.54.input_layernorm.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.A_log", - "src": "model.layers.54.linear_attn.A_log", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.conv1d.weight", - "src": "model.layers.54.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.dt_bias", - "src": "model.layers.54.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.in_proj_a.weight", - "src": "model.layers.54.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.in_proj_b.weight", - "src": "model.layers.54.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.in_proj_qkv.weight", - "src": "model.layers.54.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.in_proj_z.weight", - "src": "model.layers.54.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.norm.weight", - "src": "model.layers.54.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.linear_attn.out_proj.weight", - "src": "model.layers.54.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.mlp.down_proj.weight", - "src": "model.layers.54.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.mlp.gate_proj.weight", - "src": "model.layers.54.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.mlp.up_proj.weight", - "src": "model.layers.54.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.106.post_attention_layernorm.weight", - "src": "model.layers.54.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 106, - 54, - false - ] - }, - { - "key": "model.layers.107.input_layernorm.weight", - "src": "model.layers.55.input_layernorm.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.mlp.down_proj.weight", - "src": "model.layers.55.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.mlp.gate_proj.weight", - "src": "model.layers.55.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.mlp.up_proj.weight", - "src": "model.layers.55.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.post_attention_layernorm.weight", - "src": "model.layers.55.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.self_attn.k_norm.weight", - "src": "model.layers.55.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.self_attn.k_proj.weight", - "src": "model.layers.55.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.self_attn.o_proj.weight", - "src": "model.layers.55.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.self_attn.q_norm.weight", - "src": "model.layers.55.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.self_attn.q_proj.weight", - "src": "model.layers.55.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.107.self_attn.v_proj.weight", - "src": "model.layers.55.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 107, - 55, - false - ] - }, - { - "key": "model.layers.108.input_layernorm.weight", - "src": "model.layers.52.input_layernorm.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.A_log", - "src": "model.layers.52.linear_attn.A_log", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.conv1d.weight", - "src": "model.layers.52.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.dt_bias", - "src": "model.layers.52.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.in_proj_a.weight", - "src": "model.layers.52.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.in_proj_b.weight", - "src": "model.layers.52.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.in_proj_qkv.weight", - "src": "model.layers.52.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.in_proj_z.weight", - "src": "model.layers.52.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.norm.weight", - "src": "model.layers.52.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.linear_attn.out_proj.weight", - "src": "model.layers.52.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.mlp.down_proj.weight", - "src": "model.layers.52.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.mlp.gate_proj.weight", - "src": "model.layers.52.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.mlp.up_proj.weight", - "src": "model.layers.52.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.108.post_attention_layernorm.weight", - "src": "model.layers.52.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 108, - 52, - true - ] - }, - { - "key": "model.layers.109.input_layernorm.weight", - "src": "model.layers.53.input_layernorm.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.A_log", - "src": "model.layers.53.linear_attn.A_log", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.conv1d.weight", - "src": "model.layers.53.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.dt_bias", - "src": "model.layers.53.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.in_proj_a.weight", - "src": "model.layers.53.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.in_proj_b.weight", - "src": "model.layers.53.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.in_proj_qkv.weight", - "src": "model.layers.53.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.in_proj_z.weight", - "src": "model.layers.53.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.norm.weight", - "src": "model.layers.53.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.linear_attn.out_proj.weight", - "src": "model.layers.53.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.mlp.down_proj.weight", - "src": "model.layers.53.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.mlp.gate_proj.weight", - "src": "model.layers.53.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.mlp.up_proj.weight", - "src": "model.layers.53.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.109.post_attention_layernorm.weight", - "src": "model.layers.53.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 109, - 53, - true - ] - }, - { - "key": "model.layers.110.input_layernorm.weight", - "src": "model.layers.54.input_layernorm.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.A_log", - "src": "model.layers.54.linear_attn.A_log", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.conv1d.weight", - "src": "model.layers.54.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.dt_bias", - "src": "model.layers.54.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.in_proj_a.weight", - "src": "model.layers.54.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.in_proj_b.weight", - "src": "model.layers.54.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.in_proj_qkv.weight", - "src": "model.layers.54.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.in_proj_z.weight", - "src": "model.layers.54.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.norm.weight", - "src": "model.layers.54.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.linear_attn.out_proj.weight", - "src": "model.layers.54.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.mlp.down_proj.weight", - "src": "model.layers.54.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.mlp.gate_proj.weight", - "src": "model.layers.54.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.mlp.up_proj.weight", - "src": "model.layers.54.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.110.post_attention_layernorm.weight", - "src": "model.layers.54.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 110, - 54, - true - ] - }, - { - "key": "model.layers.111.input_layernorm.weight", - "src": "model.layers.55.input_layernorm.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.mlp.down_proj.weight", - "src": "model.layers.55.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.mlp.gate_proj.weight", - "src": "model.layers.55.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.mlp.up_proj.weight", - "src": "model.layers.55.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.post_attention_layernorm.weight", - "src": "model.layers.55.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.self_attn.k_norm.weight", - "src": "model.layers.55.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.self_attn.k_proj.weight", - "src": "model.layers.55.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.self_attn.o_proj.weight", - "src": "model.layers.55.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.self_attn.q_norm.weight", - "src": "model.layers.55.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.self_attn.q_proj.weight", - "src": "model.layers.55.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.111.self_attn.v_proj.weight", - "src": "model.layers.55.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 111, - 55, - true - ] - }, - { - "key": "model.layers.112.input_layernorm.weight", - "src": "model.layers.56.input_layernorm.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.A_log", - "src": "model.layers.56.linear_attn.A_log", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.conv1d.weight", - "src": "model.layers.56.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.dt_bias", - "src": "model.layers.56.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.in_proj_a.weight", - "src": "model.layers.56.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.in_proj_b.weight", - "src": "model.layers.56.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.in_proj_qkv.weight", - "src": "model.layers.56.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.in_proj_z.weight", - "src": "model.layers.56.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.norm.weight", - "src": "model.layers.56.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.linear_attn.out_proj.weight", - "src": "model.layers.56.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.mlp.down_proj.weight", - "src": "model.layers.56.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.mlp.gate_proj.weight", - "src": "model.layers.56.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.mlp.up_proj.weight", - "src": "model.layers.56.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.112.post_attention_layernorm.weight", - "src": "model.layers.56.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 112, - 56, - false - ] - }, - { - "key": "model.layers.113.input_layernorm.weight", - "src": "model.layers.57.input_layernorm.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.A_log", - "src": "model.layers.57.linear_attn.A_log", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.conv1d.weight", - "src": "model.layers.57.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.dt_bias", - "src": "model.layers.57.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.in_proj_a.weight", - "src": "model.layers.57.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.in_proj_b.weight", - "src": "model.layers.57.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.in_proj_qkv.weight", - "src": "model.layers.57.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.in_proj_z.weight", - "src": "model.layers.57.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.norm.weight", - "src": "model.layers.57.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.linear_attn.out_proj.weight", - "src": "model.layers.57.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.mlp.down_proj.weight", - "src": "model.layers.57.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.mlp.gate_proj.weight", - "src": "model.layers.57.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.mlp.up_proj.weight", - "src": "model.layers.57.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.113.post_attention_layernorm.weight", - "src": "model.layers.57.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 113, - 57, - false - ] - }, - { - "key": "model.layers.114.input_layernorm.weight", - "src": "model.layers.58.input_layernorm.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.A_log", - "src": "model.layers.58.linear_attn.A_log", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.conv1d.weight", - "src": "model.layers.58.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.dt_bias", - "src": "model.layers.58.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.in_proj_a.weight", - "src": "model.layers.58.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.in_proj_b.weight", - "src": "model.layers.58.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.in_proj_qkv.weight", - "src": "model.layers.58.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.in_proj_z.weight", - "src": "model.layers.58.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.norm.weight", - "src": "model.layers.58.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.linear_attn.out_proj.weight", - "src": "model.layers.58.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.mlp.down_proj.weight", - "src": "model.layers.58.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.mlp.gate_proj.weight", - "src": "model.layers.58.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.mlp.up_proj.weight", - "src": "model.layers.58.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.114.post_attention_layernorm.weight", - "src": "model.layers.58.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 114, - 58, - false - ] - }, - { - "key": "model.layers.115.input_layernorm.weight", - "src": "model.layers.59.input_layernorm.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.mlp.down_proj.weight", - "src": "model.layers.59.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.mlp.gate_proj.weight", - "src": "model.layers.59.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.mlp.up_proj.weight", - "src": "model.layers.59.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.post_attention_layernorm.weight", - "src": "model.layers.59.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.self_attn.k_norm.weight", - "src": "model.layers.59.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.self_attn.k_proj.weight", - "src": "model.layers.59.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.self_attn.o_proj.weight", - "src": "model.layers.59.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.self_attn.q_norm.weight", - "src": "model.layers.59.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.self_attn.q_proj.weight", - "src": "model.layers.59.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.115.self_attn.v_proj.weight", - "src": "model.layers.59.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 115, - 59, - false - ] - }, - { - "key": "model.layers.116.input_layernorm.weight", - "src": "model.layers.56.input_layernorm.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.A_log", - "src": "model.layers.56.linear_attn.A_log", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.conv1d.weight", - "src": "model.layers.56.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.dt_bias", - "src": "model.layers.56.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.in_proj_a.weight", - "src": "model.layers.56.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.in_proj_b.weight", - "src": "model.layers.56.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.in_proj_qkv.weight", - "src": "model.layers.56.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.in_proj_z.weight", - "src": "model.layers.56.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.norm.weight", - "src": "model.layers.56.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.linear_attn.out_proj.weight", - "src": "model.layers.56.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.mlp.down_proj.weight", - "src": "model.layers.56.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.mlp.gate_proj.weight", - "src": "model.layers.56.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.mlp.up_proj.weight", - "src": "model.layers.56.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.116.post_attention_layernorm.weight", - "src": "model.layers.56.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 116, - 56, - true - ] - }, - { - "key": "model.layers.117.input_layernorm.weight", - "src": "model.layers.57.input_layernorm.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.A_log", - "src": "model.layers.57.linear_attn.A_log", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.conv1d.weight", - "src": "model.layers.57.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.dt_bias", - "src": "model.layers.57.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.in_proj_a.weight", - "src": "model.layers.57.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.in_proj_b.weight", - "src": "model.layers.57.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.in_proj_qkv.weight", - "src": "model.layers.57.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.in_proj_z.weight", - "src": "model.layers.57.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.norm.weight", - "src": "model.layers.57.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.linear_attn.out_proj.weight", - "src": "model.layers.57.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.mlp.down_proj.weight", - "src": "model.layers.57.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.mlp.gate_proj.weight", - "src": "model.layers.57.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.mlp.up_proj.weight", - "src": "model.layers.57.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.117.post_attention_layernorm.weight", - "src": "model.layers.57.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 117, - 57, - true - ] - }, - { - "key": "model.layers.118.input_layernorm.weight", - "src": "model.layers.58.input_layernorm.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.A_log", - "src": "model.layers.58.linear_attn.A_log", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.conv1d.weight", - "src": "model.layers.58.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.dt_bias", - "src": "model.layers.58.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.in_proj_a.weight", - "src": "model.layers.58.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.in_proj_b.weight", - "src": "model.layers.58.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.in_proj_qkv.weight", - "src": "model.layers.58.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.in_proj_z.weight", - "src": "model.layers.58.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.norm.weight", - "src": "model.layers.58.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.linear_attn.out_proj.weight", - "src": "model.layers.58.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.mlp.down_proj.weight", - "src": "model.layers.58.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.mlp.gate_proj.weight", - "src": "model.layers.58.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.mlp.up_proj.weight", - "src": "model.layers.58.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.118.post_attention_layernorm.weight", - "src": "model.layers.58.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 118, - 58, - true - ] - }, - { - "key": "model.layers.119.input_layernorm.weight", - "src": "model.layers.59.input_layernorm.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.mlp.down_proj.weight", - "src": "model.layers.59.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.mlp.gate_proj.weight", - "src": "model.layers.59.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.mlp.up_proj.weight", - "src": "model.layers.59.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.post_attention_layernorm.weight", - "src": "model.layers.59.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.self_attn.k_norm.weight", - "src": "model.layers.59.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.self_attn.k_proj.weight", - "src": "model.layers.59.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.self_attn.o_proj.weight", - "src": "model.layers.59.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.self_attn.q_norm.weight", - "src": "model.layers.59.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.self_attn.q_proj.weight", - "src": "model.layers.59.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.119.self_attn.v_proj.weight", - "src": "model.layers.59.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 119, - 59, - true - ] - }, - { - "key": "model.layers.120.input_layernorm.weight", - "src": "model.layers.60.input_layernorm.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.A_log", - "src": "model.layers.60.linear_attn.A_log", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.conv1d.weight", - "src": "model.layers.60.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.dt_bias", - "src": "model.layers.60.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.in_proj_a.weight", - "src": "model.layers.60.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.in_proj_b.weight", - "src": "model.layers.60.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.in_proj_qkv.weight", - "src": "model.layers.60.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.in_proj_z.weight", - "src": "model.layers.60.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.norm.weight", - "src": "model.layers.60.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.linear_attn.out_proj.weight", - "src": "model.layers.60.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.mlp.down_proj.weight", - "src": "model.layers.60.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.mlp.gate_proj.weight", - "src": "model.layers.60.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.mlp.up_proj.weight", - "src": "model.layers.60.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.120.post_attention_layernorm.weight", - "src": "model.layers.60.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 120, - 60, - false - ] - }, - { - "key": "model.layers.121.input_layernorm.weight", - "src": "model.layers.61.input_layernorm.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.A_log", - "src": "model.layers.61.linear_attn.A_log", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.conv1d.weight", - "src": "model.layers.61.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.dt_bias", - "src": "model.layers.61.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.in_proj_a.weight", - "src": "model.layers.61.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.in_proj_b.weight", - "src": "model.layers.61.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.in_proj_qkv.weight", - "src": "model.layers.61.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.in_proj_z.weight", - "src": "model.layers.61.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.norm.weight", - "src": "model.layers.61.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.linear_attn.out_proj.weight", - "src": "model.layers.61.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.mlp.down_proj.weight", - "src": "model.layers.61.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.mlp.gate_proj.weight", - "src": "model.layers.61.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.mlp.up_proj.weight", - "src": "model.layers.61.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.121.post_attention_layernorm.weight", - "src": "model.layers.61.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 121, - 61, - false - ] - }, - { - "key": "model.layers.122.input_layernorm.weight", - "src": "model.layers.62.input_layernorm.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.A_log", - "src": "model.layers.62.linear_attn.A_log", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.conv1d.weight", - "src": "model.layers.62.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.dt_bias", - "src": "model.layers.62.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.in_proj_a.weight", - "src": "model.layers.62.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.in_proj_b.weight", - "src": "model.layers.62.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.in_proj_qkv.weight", - "src": "model.layers.62.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.in_proj_z.weight", - "src": "model.layers.62.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.norm.weight", - "src": "model.layers.62.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.linear_attn.out_proj.weight", - "src": "model.layers.62.linear_attn.out_proj.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.mlp.down_proj.weight", - "src": "model.layers.62.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.mlp.gate_proj.weight", - "src": "model.layers.62.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.mlp.up_proj.weight", - "src": "model.layers.62.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.122.post_attention_layernorm.weight", - "src": "model.layers.62.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 122, - 62, - false - ] - }, - { - "key": "model.layers.123.input_layernorm.weight", - "src": "model.layers.63.input_layernorm.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.mlp.down_proj.weight", - "src": "model.layers.63.mlp.down_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.mlp.gate_proj.weight", - "src": "model.layers.63.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.mlp.up_proj.weight", - "src": "model.layers.63.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.post_attention_layernorm.weight", - "src": "model.layers.63.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.self_attn.k_norm.weight", - "src": "model.layers.63.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.self_attn.k_proj.weight", - "src": "model.layers.63.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.self_attn.o_proj.weight", - "src": "model.layers.63.self_attn.o_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.self_attn.q_norm.weight", - "src": "model.layers.63.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.self_attn.q_proj.weight", - "src": "model.layers.63.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.123.self_attn.v_proj.weight", - "src": "model.layers.63.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 123, - 63, - false - ] - }, - { - "key": "model.layers.124.input_layernorm.weight", - "src": "model.layers.60.input_layernorm.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.A_log", - "src": "model.layers.60.linear_attn.A_log", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.conv1d.weight", - "src": "model.layers.60.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.dt_bias", - "src": "model.layers.60.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.in_proj_a.weight", - "src": "model.layers.60.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.in_proj_b.weight", - "src": "model.layers.60.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.in_proj_qkv.weight", - "src": "model.layers.60.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.in_proj_z.weight", - "src": "model.layers.60.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.norm.weight", - "src": "model.layers.60.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.linear_attn.out_proj.weight", - "src": "model.layers.60.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.mlp.down_proj.weight", - "src": "model.layers.60.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.mlp.gate_proj.weight", - "src": "model.layers.60.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.mlp.up_proj.weight", - "src": "model.layers.60.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.124.post_attention_layernorm.weight", - "src": "model.layers.60.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 124, - 60, - true - ] - }, - { - "key": "model.layers.125.input_layernorm.weight", - "src": "model.layers.61.input_layernorm.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.A_log", - "src": "model.layers.61.linear_attn.A_log", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.conv1d.weight", - "src": "model.layers.61.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.dt_bias", - "src": "model.layers.61.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.in_proj_a.weight", - "src": "model.layers.61.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.in_proj_b.weight", - "src": "model.layers.61.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.in_proj_qkv.weight", - "src": "model.layers.61.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.in_proj_z.weight", - "src": "model.layers.61.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.norm.weight", - "src": "model.layers.61.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.linear_attn.out_proj.weight", - "src": "model.layers.61.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.mlp.down_proj.weight", - "src": "model.layers.61.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.mlp.gate_proj.weight", - "src": "model.layers.61.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.mlp.up_proj.weight", - "src": "model.layers.61.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.125.post_attention_layernorm.weight", - "src": "model.layers.61.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 125, - 61, - true - ] - }, - { - "key": "model.layers.126.input_layernorm.weight", - "src": "model.layers.62.input_layernorm.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.A_log", - "src": "model.layers.62.linear_attn.A_log", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.conv1d.weight", - "src": "model.layers.62.linear_attn.conv1d.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.dt_bias", - "src": "model.layers.62.linear_attn.dt_bias", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.in_proj_a.weight", - "src": "model.layers.62.linear_attn.in_proj_a.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.in_proj_b.weight", - "src": "model.layers.62.linear_attn.in_proj_b.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.in_proj_qkv.weight", - "src": "model.layers.62.linear_attn.in_proj_qkv.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.in_proj_z.weight", - "src": "model.layers.62.linear_attn.in_proj_z.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.norm.weight", - "src": "model.layers.62.linear_attn.norm.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.linear_attn.out_proj.weight", - "src": "model.layers.62.linear_attn.out_proj.weight", - "op": "zero", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.mlp.down_proj.weight", - "src": "model.layers.62.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.mlp.gate_proj.weight", - "src": "model.layers.62.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.mlp.up_proj.weight", - "src": "model.layers.62.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.126.post_attention_layernorm.weight", - "src": "model.layers.62.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 126, - 62, - true - ] - }, - { - "key": "model.layers.127.input_layernorm.weight", - "src": "model.layers.63.input_layernorm.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.mlp.down_proj.weight", - "src": "model.layers.63.mlp.down_proj.weight", - "op": "zero", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.mlp.gate_proj.weight", - "src": "model.layers.63.mlp.gate_proj.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.mlp.up_proj.weight", - "src": "model.layers.63.mlp.up_proj.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.post_attention_layernorm.weight", - "src": "model.layers.63.post_attention_layernorm.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.self_attn.k_norm.weight", - "src": "model.layers.63.self_attn.k_norm.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.self_attn.k_proj.weight", - "src": "model.layers.63.self_attn.k_proj.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.self_attn.o_proj.weight", - "src": "model.layers.63.self_attn.o_proj.weight", - "op": "zero", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.self_attn.q_norm.weight", - "src": "model.layers.63.self_attn.q_norm.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.self_attn.q_proj.weight", - "src": "model.layers.63.self_attn.q_proj.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.layers.127.self_attn.v_proj.weight", - "src": "model.layers.63.self_attn.v_proj.weight", - "op": "copy", - "layer": [ - 127, - 63, - true - ] - }, - { - "key": "model.norm.weight", - "src": "model.norm.weight", - "op": "copy" - }, - { - "key": "lm_head.weight", - "src": "lm_head.weight", - "op": "copy" - }, - { - "key": "mtp.fc.weight", - "src": "mtp.fc.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.input_layernorm.weight", - "src": "mtp.layers.0.input_layernorm.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.mlp.down_proj.weight", - "src": "mtp.layers.0.mlp.down_proj.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.mlp.gate_proj.weight", - "src": "mtp.layers.0.mlp.gate_proj.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.mlp.up_proj.weight", - "src": "mtp.layers.0.mlp.up_proj.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.post_attention_layernorm.weight", - "src": "mtp.layers.0.post_attention_layernorm.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.self_attn.k_norm.weight", - "src": "mtp.layers.0.self_attn.k_norm.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.self_attn.k_proj.weight", - "src": "mtp.layers.0.self_attn.k_proj.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.self_attn.o_proj.weight", - "src": "mtp.layers.0.self_attn.o_proj.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.self_attn.q_norm.weight", - "src": "mtp.layers.0.self_attn.q_norm.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.self_attn.q_proj.weight", - "src": "mtp.layers.0.self_attn.q_proj.weight", - "op": "copy" - }, - { - "key": "mtp.layers.0.self_attn.v_proj.weight", - "src": "mtp.layers.0.self_attn.v_proj.weight", - "op": "copy" - }, - { - "key": "mtp.norm.weight", - "src": "mtp.norm.weight", - "op": "copy" - }, - { - "key": "mtp.pre_fc_norm_embedding.weight", - "src": "mtp.pre_fc_norm_embedding.weight", - "op": "copy" - }, - { - "key": "mtp.pre_fc_norm_hidden.weight", - "src": "mtp.pre_fc_norm_hidden.weight", - "op": "copy" - } - ] -} \ No newline at end of file