| { | |
| "metadata": { | |
| "total_size": 30234513408 | |
| }, | |
| "weight_map": { | |
| "language_model.lm_head.weight": "model-00007-of-00007.safetensors", | |
| "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", | |
| "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", | |
| "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "language_model.model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", | |
| "language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", | |
| "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", | |
| "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", | |
| "language_model.model.norm.weight": "model-00006-of-00007.safetensors", | |
| "multi_modal_projector.layer_norm.bias": "model-00001-of-00007.safetensors", | |
| "multi_modal_projector.layer_norm.weight": "model-00001-of-00007.safetensors", | |
| "multi_modal_projector.linear_1.bias": "model-00001-of-00007.safetensors", | |
| "multi_modal_projector.linear_1.weight": "model-00001-of-00007.safetensors", | |
| "multi_modal_projector.linear_2.bias": "model-00001-of-00007.safetensors", | |
| "multi_modal_projector.linear_2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.embeddings.cls_token": "model-00001-of-00007.safetensors", | |
| "vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.embeddings.position_embeddings": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.0.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.1.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.10.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.11.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.12.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.13.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.14.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.15.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.16.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.17.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.18.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.19.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.2.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.20.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.21.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.22.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.23.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.3.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.4.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.5.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.6.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.7.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.8.mlp.fc2.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.k_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.k_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.projection_layer.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.projection_layer.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.q_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.q_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.v_proj.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.attention.v_proj.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.lambda_1": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.lambda_2": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.layernorm_after.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.layernorm_after.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.layernorm_before.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.layernorm_before.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.mlp.fc1.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.mlp.fc1.weight": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.mlp.fc2.bias": "model-00001-of-00007.safetensors", | |
| "vision_tower.encoder.layer.9.mlp.fc2.weight": "model-00001-of-00007.safetensors" | |
| } | |
| } | |