| { | |
| "metadata": { | |
| "total_size": 23952965824 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.mlp.deepspeed_moe.gate.wg.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", | |
| "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", | |
| "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.region_fea_adapter.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.region_fea_adapter.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.text_hidden_fcs.0.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.text_hidden_fcs.0.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.text_hidden_fcs.0.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.text_hidden_fcs.0.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.0.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.1.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.10.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.11.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.2.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.3.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.4.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.5.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.6.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.7.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.8.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.Adapter.channel.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.Adapter.channel.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.Adapter.norm.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.Adapter.norm.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.Adapter.spatial.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.Adapter.spatial.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.attn.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.attn.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.attn.qkv.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.attn.qkv.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.attn.rel_pos_h": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.attn.rel_pos_w": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.blocks.9.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.neck.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.neck.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.neck.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.neck.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.neck.3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.neck.3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.patch_embed.proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.patch_embed.proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.image_encoder.pos_embed": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_prediction_head.layers.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_prediction_head.layers.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_prediction_head.layers.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_prediction_head.layers.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_prediction_head.layers.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_prediction_head.layers.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.iou_token.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.mask_tokens.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.0.layers.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.0.layers.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.0.layers.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.0.layers.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.0.layers.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.0.layers.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.1.layers.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.1.layers.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.1.layers.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.1.layers.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.1.layers.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.1.layers.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.2.layers.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.2.layers.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.2.layers.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.2.layers.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.2.layers.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.2.layers.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.3.layers.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.3.layers.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.3.layers.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.3.layers.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.3.layers.2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_hypernetworks_mlps.3.layers.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_upscaling.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_upscaling.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_upscaling.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_upscaling.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_upscaling.3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.output_upscaling.3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.final_attn_token_to_image.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_image_to_token.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.cross_attn_token_to_image.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm4.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.norm4.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_image_to_token.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.cross_attn_token_to_image.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.mlp.lin1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.mlp.lin1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.mlp.lin2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.mlp.lin2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm2.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm4.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.norm4.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.norm_final_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.mask_decoder.transformer.norm_final_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.0.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.1.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.3.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.3.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.4.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.4.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.6.bias": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.mask_downscaling.6.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.no_mask_embed.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.not_a_point_embed.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.pe_layer.positional_encoding_gaussian_matrix": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.point_embeddings.0.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.point_embeddings.1.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.point_embeddings.2.weight": "pytorch_model-00003-of-00003.bin", | |
| "model.visual_model.prompt_encoder.point_embeddings.3.weight": "pytorch_model-00003-of-00003.bin" | |
| } | |
| } | |