AnwenHu commited on
Commit
7d1aed8
1 Parent(s): 49fe235

Upload pytorch_model.bin.index.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. pytorch_model.bin.index.json +1 -0
pytorch_model.bin.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model.bin", "model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model.bin", "model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model.bin", "model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model.bin", "model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model.bin", "model.embed_tokens.weight": "pytorch_model.bin", "model.norm.weight": "pytorch_model.bin", "lm_head.weight": "pytorch_model.bin", "model.vision_model.embeddings.cls_token": "pytorch_model.bin", "model.vision_model.embeddings.patch_embed.weight": "pytorch_model.bin", "model.vision_model.embeddings.position_embedding": "pytorch_model.bin", "model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model.bin", "model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model.bin", "model.vision_model.post_layernorm.bias": "pytorch_model.bin", "model.vision_model.post_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model.bin", "model.vision2text.ln_q.weight": "pytorch_model.bin", "model.vision2text.ln_q.bias": "pytorch_model.bin", "model.vision2text.visual_fc.bias": "pytorch_model.bin", "model.vision2text.visual_fc.weight": "pytorch_model.bin", "model.vision2text.vit_eos": "pytorch_model.bin", "model.vision2text.reducer_before.0.weight": "pytorch_model.bin", "model.vision2text.reducer_before.0.bias": "pytorch_model.bin", "model.vision2text.reducer.weight": "pytorch_model.bin", "model.vision2text.reducer.bias": "pytorch_model.bin"}, "metadata": {"total_size": 265442164736}}