| { | |
| "metadata": { | |
| "total_size": 27120484136 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.mm_projector.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.mm_projector.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.running_var": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.conv1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.conv2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.conv3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.encoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.0.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.0.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.0.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.0.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.1.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.1.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.1.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.1.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.2.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.2.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.2.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.2.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.3.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.3.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.3.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.input_proj.3.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.level_embed": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.query_position_embeddings.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.reference_points.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.0.reference_points.weight": "pytorch_model-00003-of-00003.bin" | |
| } | |
| } | |