| { | |
| "metadata": { | |
| "total_parameters": 3154854076, | |
| "total_size": 12673176304 | |
| }, | |
| "weight_map": { | |
| "fusion_project.bias": "model-00003-of-00003.safetensors", | |
| "fusion_project.weight": "model-00003-of-00003.safetensors", | |
| "itformer.cycle_pos.pe": "model-00003-of-00003.safetensors", | |
| "itformer.instruc_pos.pe": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_instruct.0.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_instruct.0.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_instruct.1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_instruct.1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_instruct.4.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_instruct.4.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_prefix.0.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_prefix.0.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_prefix.1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_prefix.1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_prefix.4.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.feed_forward_prefix.4.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.channel_key_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.channel_key_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.channel_query_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.channel_query_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.channel_value_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.channel_value_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.key_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.key_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.query_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.query_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.value_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.attn_it.value_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.norm1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.it_attn.norm1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.self_attn.attn_seq.proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.self_attn.attn_seq.proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.self_attn.attn_seq.qkv.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.self_attn.attn_seq.qkv.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.self_attn.norm1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.0.self_attn.norm1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_instruct.0.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_instruct.0.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_instruct.1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_instruct.1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_instruct.4.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_instruct.4.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_prefix.0.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_prefix.0.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_prefix.1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_prefix.1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_prefix.4.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.feed_forward_prefix.4.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.channel_key_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.channel_key_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.channel_query_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.channel_query_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.channel_value_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.channel_value_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.key_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.key_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.query_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.query_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.value_proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.attn_it.value_proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.norm1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.it_attn.norm1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.self_attn.attn_seq.proj.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.self_attn.attn_seq.proj.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.self_attn.attn_seq.qkv.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.self_attn.attn_seq.qkv.weight": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.self_attn.norm1.bias": "model-00003-of-00003.safetensors", | |
| "itformer.layers.1.self_attn.norm1.weight": "model-00003-of-00003.safetensors", | |
| "itformer.norm.bias": "model-00003-of-00003.safetensors", | |
| "itformer.norm.weight": "model-00003-of-00003.safetensors", | |
| "itformer.prefix_token": "model-00003-of-00003.safetensors", | |
| "itformer.time_pos.pe": "model-00003-of-00003.safetensors", | |
| "itformer.var_pos.pe": "model-00003-of-00003.safetensors", | |
| "llm_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", | |
| "llm_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", | |
| "llm_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", | |
| "llm_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", | |
| "llm_model.model.norm.weight": "model-00003-of-00003.safetensors", | |
| "query_project.bias": "model-00003-of-00003.safetensors", | |
| "query_project.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.feed_forward.fc1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.feed_forward.fc1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.feed_forward.fc2.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.feed_forward.fc2.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.var_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.0.var_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.feed_forward.fc1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.feed_forward.fc1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.feed_forward.fc2.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.feed_forward.fc2.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.var_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.1.var_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.feed_forward.fc1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.feed_forward.fc1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.feed_forward.fc2.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.feed_forward.fc2.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.var_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.2.var_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.feed_forward.fc1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.feed_forward.fc1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.feed_forward.fc2.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.feed_forward.fc2.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.seq_att_block.attn_seq.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.seq_att_block.attn_seq.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.seq_att_block.attn_seq.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.seq_att_block.attn_seq.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.seq_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.seq_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.var_att_block.attn_var.proj.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.var_att_block.attn_var.proj.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.var_att_block.attn_var.qkv.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.var_att_block.attn_var.qkv.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.var_att_block.norm1.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.layers.3.var_att_block.norm1.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.norm.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.norm.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.patch_embedding.0.weight": "model-00003-of-00003.safetensors", | |
| "ts_encoder.proj_head.bias": "model-00003-of-00003.safetensors", | |
| "ts_encoder.proj_head.weight": "model-00003-of-00003.safetensors", | |
| "ts_project.bias": "model-00003-of-00003.safetensors", | |
| "ts_project.weight": "model-00003-of-00003.safetensors" | |
| } | |
| } | |