Text Generation
Transformers
PyTorch
llava
Inference Endpoints
ConvLLaVA-pretrain-1024 / pytorch_model.bin.index.json
ChunjiangGe's picture
Upload pytorch_model.bin.index.json with huggingface_hub
1962cde verified
{
"metadata": {
"total_size": 14873903488
},
"weight_map": {
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
"model.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
"model.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
"model.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
"model.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
"model.norm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.embeddings.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.embeddings.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.embeddings.patch_embeddings.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.embeddings.patch_embeddings.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.0.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.1.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.0.layers.2.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.downsampling_layer.0.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.downsampling_layer.0.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.downsampling_layer.1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.downsampling_layer.1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.0.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.1.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.1.layers.2.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.downsampling_layer.0.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.downsampling_layer.0.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.downsampling_layer.1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.downsampling_layer.1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.0.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.1.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.10.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.11.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.12.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.13.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.14.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.15.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.16.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.17.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.18.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.19.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.2.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.20.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.21.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.22.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.23.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.24.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.25.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.26.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.3.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.4.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.5.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.6.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.7.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.8.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.2.layers.9.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.downsampling_layer.0.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.downsampling_layer.0.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.downsampling_layer.1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.downsampling_layer.1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.0.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.1.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.3.layers.2.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.downsampling_layer.0.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.downsampling_layer.0.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.downsampling_layer.1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.downsampling_layer.1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.0.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.1.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.2.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.3.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.4.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.dwconv.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.dwconv.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.layer_scale_parameter": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.layernorm.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.pwconv1.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.pwconv1.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.pwconv2.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.encoder.stages.4.layers.5.pwconv2.weight": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.layernorm.bias": "pytorch_model-00002-of-00002.bin",
"model.vision_tower.vision_tower.layernorm.weight": "pytorch_model-00002-of-00002.bin"
}
}