blip2zh-chatglm-6b / pytorch_model.bin.index.json
shwu
feat: better modeling_blip2chatglm
769e287
{
"metadata": {
"total_size": 15821012736
},
"weight_map": {
"language_model.lm_head.weight": "pytorch_model-00009-of-00009.bin",
"language_model.transformer.final_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.final_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.0.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.1.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.1.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"language_model.transformer.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.10.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.11.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"language_model.transformer.layers.16.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.2.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.20.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.20.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"language_model.transformer.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.25.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.25.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"language_model.transformer.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"language_model.transformer.layers.3.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.6.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.6.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"language_model.transformer.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"language_model.transformer.word_embeddings.weight": "pytorch_model-00002-of-00009.bin",
"language_projection.bias": "pytorch_model-00002-of-00009.bin",
"language_projection.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.attention.key.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.attention.key.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.attention.query.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.attention.query.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.attention.value.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.attention.value.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00009.bin",
"qformer.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.0.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.0.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.1.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.10.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.11.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.2.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.3.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.4.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.5.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.6.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.7.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.8.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.output_query.dense.bias": "pytorch_model-00002-of-00009.bin",
"qformer.encoder.layer.9.output_query.dense.weight": "pytorch_model-00002-of-00009.bin",
"qformer.layernorm.bias": "pytorch_model-00001-of-00009.bin",
"qformer.layernorm.weight": "pytorch_model-00001-of-00009.bin",
"query_tokens": "pytorch_model-00001-of-00009.bin",
"vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00009.bin",
"vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00009.bin",
"vision_model.post_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"vision_model.post_layernorm.weight": "pytorch_model-00001-of-00009.bin"
}
}