diff --git "a/pytorch_model.bin.index.json" "b/pytorch_model.bin.index.json" new file mode 100644--- /dev/null +++ "b/pytorch_model.bin.index.json" @@ -0,0 +1,1227 @@ +{ + "metadata": { + "total_size": 27143718230 + }, + "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.router.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-00001-of-00003.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-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-00001-of-00003.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.router.weight": "pytorch_model-00001-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-00001-of-00003.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-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-00001-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.router.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-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.router.weight": "pytorch_model-00001-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-00002-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-00002-of-00003.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.router.weight": "pytorch_model-00001-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-00002-of-00003.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-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.router.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-00002-of-00003.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-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.router.weight": "pytorch_model-00001-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.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.router.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.39.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.router.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.router.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.router.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.router.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.router.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.router.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.0.bias": "pytorch_model-00003-of-00003.bin", + "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin", + "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin", + "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin", + "model.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages.0.fast_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages.0.fast_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages.0.slow_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages.0.slow_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.fast_conv.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.fast_conv.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.fast_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.fast_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.gate.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.gate.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.gate.2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.gate.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.slow_conv.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.slow_conv.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.slow_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.0.slow_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.fast_conv.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.fast_conv.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.fast_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.fast_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.gate.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.gate.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.gate.2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.gate.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.slow_conv.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.slow_conv.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.slow_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.1.slow_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.fast_conv.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.fast_conv.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.fast_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.fast_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.gate.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.gate.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.gate.2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.gate.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.slow_conv.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.slow_conv.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.slow_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.align_stages_latent.2.slow_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.fast_vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.head.fc.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.head.fc.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.head.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.head.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.head.pre_logits.fc.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.head.pre_logits.fc.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.0.blocks.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.blocks.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.downsample.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.downsample.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.downsample.1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.1.downsample.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.10.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.11.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.12.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.13.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.14.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.15.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.16.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.17.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.18.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.19.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.20.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.21.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.22.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.23.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.24.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.25.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.26.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.3.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.4.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.5.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.6.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.7.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.8.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.blocks.9.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.downsample.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.downsample.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.downsample.1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.2.downsample.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.conv_dw.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.conv_dw.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.norm.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.norm.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.blocks.2.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.downsample.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.downsample.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.downsample.1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stages.3.downsample.1.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stem.0.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stem.0.weight": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stem.1.bias": "pytorch_model-00003-of-00003.bin", + "model.vision_tower.slow_vision_tower.vision_tower.stem.1.weight": "pytorch_model-00003-of-00003.bin" + } +}