pytorch_model.bin.index.json

{"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-1-of-33.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-2-of-33.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-3-of-33.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-4-of-33.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-5-of-33.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-6-of-33.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-7-of-33.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-8-of-33.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-9-of-33.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-10-of-33.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-33.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-12-of-33.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-13-of-33.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-33.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-15-of-33.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-16-of-33.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-33.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-18-of-33.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-19-of-33.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-33.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-21-of-33.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-22-of-33.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-33.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-24-of-33.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-25-of-33.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-33.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-27-of-33.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-28-of-33.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-33.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-30-of-33.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-31-of-33.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-33.bin", "model.embed_tokens.weight": "pytorch_model-33-of-33.bin", "model.norm.weight": "pytorch_model-33-of-33.bin", "lm_head.weight": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.cls_token": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.patch_embed.weight": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.position_embedding": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.post_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.post_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.query_embeds": "pytorch_model-33-of-33.bin", "model.visual_abstractor.visual_fc.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.visual_fc.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.vit_eos": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin"}, "metadata": {"total_size": 16395722752}}