{ "metadata": { "total_size": 36585347456 }, "weight_map": { "lm_head.weight": "model-00008-of-00008.safetensors", "model.cross_vision.pos_embed": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.0.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.1.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.10.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.11.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.12.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.13.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.14.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.15.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.16.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.17.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.18.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.19.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.2.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.20.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.21.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.22.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.23.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.3.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.4.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.5.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.6.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.7.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.8.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.inner_attn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.inner_attn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.q_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.v_bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.ffn_ln.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.ffn_ln.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.w1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.w1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.w2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.w2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.w3.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.mlp.w3.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.norm1.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.norm1.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.norm2.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.blocks.9.norm2.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.cls_token": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.head.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.head.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.norm.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.norm.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.patch_embed.proj.bias": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.patch_embed.proj.weight": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.pos_embed": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.rope.freqs_cos": "model-00008-of-00008.safetensors", "model.cross_vision.vit.model.rope.freqs_sin": "model-00008-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.cross_attn.dense.weight": "model-00001-of-00008.safetensors", "model.layers.0.cross_attn.key_value.weight": "model-00001-of-00008.safetensors", "model.layers.0.cross_attn.query.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.language_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.language_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.language_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.vision_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.vision_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.vision_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_cross_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.language_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.language_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.vision_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.vision_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.1.cross_attn.dense.weight": "model-00001-of-00008.safetensors", "model.layers.1.cross_attn.key_value.weight": "model-00001-of-00008.safetensors", "model.layers.1.cross_attn.query.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.language_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.language_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.language_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.vision_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.vision_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.vision_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_cross_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.language_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.language_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.vision_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.vision_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.10.cross_attn.dense.weight": "model-00002-of-00008.safetensors", "model.layers.10.cross_attn.key_value.weight": "model-00002-of-00008.safetensors", "model.layers.10.cross_attn.query.weight": "model-00002-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.language_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.language_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.language_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.vision_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.vision_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.mlp.vision_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.post_cross_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.language_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.language_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.vision_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.10.self_attn.vision_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.11.cross_attn.dense.weight": "model-00002-of-00008.safetensors", "model.layers.11.cross_attn.key_value.weight": "model-00002-of-00008.safetensors", "model.layers.11.cross_attn.query.weight": "model-00002-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.language_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.language_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.language_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.vision_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.vision_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.vision_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_cross_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.language_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.language_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.vision_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.vision_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.12.cross_attn.dense.weight": "model-00003-of-00008.safetensors", "model.layers.12.cross_attn.key_value.weight": "model-00003-of-00008.safetensors", "model.layers.12.cross_attn.query.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.language_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.language_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.language_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.vision_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.vision_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.vision_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_cross_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.language_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.language_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.vision_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.vision_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.13.cross_attn.dense.weight": "model-00003-of-00008.safetensors", "model.layers.13.cross_attn.key_value.weight": "model-00003-of-00008.safetensors", "model.layers.13.cross_attn.query.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.language_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.language_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.language_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.vision_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.vision_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.mlp.vision_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_cross_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.language_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.language_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.vision_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.vision_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.14.cross_attn.dense.weight": "model-00003-of-00008.safetensors", "model.layers.14.cross_attn.key_value.weight": "model-00003-of-00008.safetensors", "model.layers.14.cross_attn.query.weight": "model-00003-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.language_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.language_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.language_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.vision_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.vision_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.mlp.vision_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.post_cross_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.language_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.language_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.vision_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.14.self_attn.vision_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.15.cross_attn.dense.weight": "model-00003-of-00008.safetensors", "model.layers.15.cross_attn.key_value.weight": "model-00003-of-00008.safetensors", "model.layers.15.cross_attn.query.weight": "model-00003-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.language_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.language_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.language_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.vision_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.vision_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.mlp.vision_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.post_cross_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.language_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.language_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.vision_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.15.self_attn.vision_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.16.cross_attn.dense.weight": "model-00003-of-00008.safetensors", "model.layers.16.cross_attn.key_value.weight": "model-00003-of-00008.safetensors", "model.layers.16.cross_attn.query.weight": "model-00003-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.language_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.language_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.language_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.vision_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.vision_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.vision_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_cross_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.language_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.language_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.vision_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.vision_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.17.cross_attn.dense.weight": "model-00003-of-00008.safetensors", "model.layers.17.cross_attn.key_value.weight": "model-00003-of-00008.safetensors", "model.layers.17.cross_attn.query.weight": "model-00003-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.language_mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.language_mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.language_mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.vision_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.vision_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.vision_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_cross_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.language_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.language_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.vision_expert_dense.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.vision_expert_query_key_value.weight": "model-00003-of-00008.safetensors", "model.layers.18.cross_attn.dense.weight": "model-00004-of-00008.safetensors", "model.layers.18.cross_attn.key_value.weight": "model-00004-of-00008.safetensors", "model.layers.18.cross_attn.query.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.language_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.language_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.language_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.vision_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.vision_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.vision_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_cross_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.language_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.language_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.vision_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.vision_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.19.cross_attn.dense.weight": "model-00004-of-00008.safetensors", "model.layers.19.cross_attn.key_value.weight": "model-00004-of-00008.safetensors", "model.layers.19.cross_attn.query.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.language_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.language_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.language_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.vision_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.vision_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.vision_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_cross_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.language_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.language_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.vision_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.vision_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.2.cross_attn.dense.weight": "model-00001-of-00008.safetensors", "model.layers.2.cross_attn.key_value.weight": "model-00001-of-00008.safetensors", "model.layers.2.cross_attn.query.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.language_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.language_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.language_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.vision_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.vision_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.vision_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_cross_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.language_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.language_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.vision_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.vision_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.20.cross_attn.dense.weight": "model-00004-of-00008.safetensors", "model.layers.20.cross_attn.key_value.weight": "model-00004-of-00008.safetensors", "model.layers.20.cross_attn.query.weight": "model-00004-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.language_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.language_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.language_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.vision_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.vision_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.vision_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_cross_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.language_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.language_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.vision_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.vision_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.21.cross_attn.dense.weight": "model-00004-of-00008.safetensors", "model.layers.21.cross_attn.key_value.weight": "model-00004-of-00008.safetensors", "model.layers.21.cross_attn.query.weight": "model-00004-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.language_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.language_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.language_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.vision_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.vision_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.vision_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.post_cross_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.language_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.language_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.vision_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.vision_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.22.cross_attn.dense.weight": "model-00004-of-00008.safetensors", "model.layers.22.cross_attn.key_value.weight": "model-00004-of-00008.safetensors", "model.layers.22.cross_attn.query.weight": "model-00004-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.language_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.language_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.language_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.vision_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.vision_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.vision_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.post_cross_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.language_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.language_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.vision_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.vision_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.23.cross_attn.dense.weight": "model-00004-of-00008.safetensors", "model.layers.23.cross_attn.key_value.weight": "model-00004-of-00008.safetensors", "model.layers.23.cross_attn.query.weight": "model-00004-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.language_mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.language_mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.language_mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.vision_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.vision_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.mlp.vision_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_cross_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.language_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.language_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.vision_expert_dense.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.vision_expert_query_key_value.weight": "model-00004-of-00008.safetensors", "model.layers.24.cross_attn.dense.weight": "model-00005-of-00008.safetensors", "model.layers.24.cross_attn.key_value.weight": "model-00005-of-00008.safetensors", "model.layers.24.cross_attn.query.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.language_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.language_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.language_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.vision_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.vision_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.mlp.vision_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_cross_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.language_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.language_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.vision_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.vision_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.25.cross_attn.dense.weight": "model-00005-of-00008.safetensors", "model.layers.25.cross_attn.key_value.weight": "model-00005-of-00008.safetensors", "model.layers.25.cross_attn.query.weight": "model-00005-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.language_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.language_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.language_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.vision_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.vision_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.vision_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_cross_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.language_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.language_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.vision_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.vision_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.26.cross_attn.dense.weight": "model-00005-of-00008.safetensors", "model.layers.26.cross_attn.key_value.weight": "model-00005-of-00008.safetensors", "model.layers.26.cross_attn.query.weight": "model-00005-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.language_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.language_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.language_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.vision_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.vision_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.vision_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.post_cross_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.language_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.language_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.vision_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.vision_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.27.cross_attn.dense.weight": "model-00005-of-00008.safetensors", "model.layers.27.cross_attn.key_value.weight": "model-00005-of-00008.safetensors", "model.layers.27.cross_attn.query.weight": "model-00005-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.language_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.language_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.language_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.vision_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.vision_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.vision_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.post_cross_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.language_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.language_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.vision_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.vision_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.28.cross_attn.dense.weight": "model-00005-of-00008.safetensors", "model.layers.28.cross_attn.key_value.weight": "model-00005-of-00008.safetensors", "model.layers.28.cross_attn.query.weight": "model-00005-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.language_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.language_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.language_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.vision_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.vision_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.vision_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.28.post_cross_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.language_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.language_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.vision_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.vision_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.29.cross_attn.dense.weight": "model-00005-of-00008.safetensors", "model.layers.29.cross_attn.key_value.weight": "model-00005-of-00008.safetensors", "model.layers.29.cross_attn.query.weight": "model-00005-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.language_mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.29.mlp.language_mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.29.mlp.language_mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.29.mlp.vision_mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.vision_mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.vision_mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_cross_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.language_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.29.self_attn.language_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00005-of-00008.safetensors", "model.layers.29.self_attn.vision_expert_dense.weight": "model-00005-of-00008.safetensors", "model.layers.29.self_attn.vision_expert_query_key_value.weight": "model-00005-of-00008.safetensors", "model.layers.3.cross_attn.dense.weight": "model-00001-of-00008.safetensors", "model.layers.3.cross_attn.key_value.weight": "model-00001-of-00008.safetensors", "model.layers.3.cross_attn.query.weight": "model-00001-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.language_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.language_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.language_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.vision_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.vision_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.vision_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.post_cross_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.language_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.language_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.vision_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.vision_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.30.cross_attn.dense.weight": "model-00006-of-00008.safetensors", "model.layers.30.cross_attn.key_value.weight": "model-00006-of-00008.safetensors", "model.layers.30.cross_attn.query.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.language_mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.language_mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.language_mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.vision_mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.vision_mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.vision_mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_cross_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.language_expert_dense.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.language_expert_query_key_value.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.vision_expert_dense.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.vision_expert_query_key_value.weight": "model-00006-of-00008.safetensors", "model.layers.31.cross_attn.dense.weight": "model-00006-of-00008.safetensors", "model.layers.31.cross_attn.key_value.weight": "model-00006-of-00008.safetensors", "model.layers.31.cross_attn.query.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.language_mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.language_mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.language_mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.vision_mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.vision_mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.vision_mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_cross_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.language_expert_dense.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.language_expert_query_key_value.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.vision_expert_dense.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.vision_expert_query_key_value.weight": "model-00006-of-00008.safetensors", "model.layers.4.cross_attn.dense.weight": "model-00001-of-00008.safetensors", "model.layers.4.cross_attn.key_value.weight": "model-00001-of-00008.safetensors", "model.layers.4.cross_attn.query.weight": "model-00001-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.language_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.language_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.language_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.vision_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.vision_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.mlp.vision_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.post_cross_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.language_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.language_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.vision_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.4.self_attn.vision_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.5.cross_attn.dense.weight": "model-00001-of-00008.safetensors", "model.layers.5.cross_attn.key_value.weight": "model-00001-of-00008.safetensors", "model.layers.5.cross_attn.query.weight": "model-00001-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.language_mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.language_mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.language_mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.5.mlp.vision_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.vision_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.vision_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_cross_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.language_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.language_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.vision_expert_dense.weight": "model-00001-of-00008.safetensors", "model.layers.5.self_attn.vision_expert_query_key_value.weight": "model-00001-of-00008.safetensors", "model.layers.6.cross_attn.dense.weight": "model-00002-of-00008.safetensors", "model.layers.6.cross_attn.key_value.weight": "model-00002-of-00008.safetensors", "model.layers.6.cross_attn.query.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.language_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.language_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.language_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.vision_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.vision_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.vision_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_cross_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.language_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.language_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.vision_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.vision_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.7.cross_attn.dense.weight": "model-00002-of-00008.safetensors", "model.layers.7.cross_attn.key_value.weight": "model-00002-of-00008.safetensors", "model.layers.7.cross_attn.query.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.language_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.language_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.language_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.vision_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.vision_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.vision_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_cross_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.language_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.language_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.vision_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.vision_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.8.cross_attn.dense.weight": "model-00002-of-00008.safetensors", "model.layers.8.cross_attn.key_value.weight": "model-00002-of-00008.safetensors", "model.layers.8.cross_attn.query.weight": "model-00002-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.language_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.language_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.language_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.vision_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.vision_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.mlp.vision_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.post_cross_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.language_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.language_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.vision_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.8.self_attn.vision_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.9.cross_attn.dense.weight": "model-00002-of-00008.safetensors", "model.layers.9.cross_attn.key_value.weight": "model-00002-of-00008.safetensors", "model.layers.9.cross_attn.query.weight": "model-00002-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.language_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.language_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.language_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.vision_mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.vision_mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.mlp.vision_mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.post_cross_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.language_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.language_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.vision_expert_dense.weight": "model-00002-of-00008.safetensors", "model.layers.9.self_attn.vision_expert_query_key_value.weight": "model-00002-of-00008.safetensors", "model.norm.weight": "model-00006-of-00008.safetensors", "model.vision.boi": "model-00006-of-00008.safetensors", "model.vision.eoi": "model-00006-of-00008.safetensors", "model.vision.linear_proj.dense_4h_to_h.weight": "model-00008-of-00008.safetensors", "model.vision.linear_proj.dense_h_to_4h.weight": "model-00008-of-00008.safetensors", "model.vision.linear_proj.gate_proj.weight": "model-00008-of-00008.safetensors", "model.vision.linear_proj.linear_proj.weight": "model-00008-of-00008.safetensors", "model.vision.linear_proj.norm1.bias": "model-00008-of-00008.safetensors", "model.vision.linear_proj.norm1.weight": "model-00008-of-00008.safetensors", "model.vision.patch_embedding.cls_embedding": "model-00006-of-00008.safetensors", "model.vision.patch_embedding.position_embedding.weight": "model-00006-of-00008.safetensors", "model.vision.patch_embedding.proj.bias": "model-00006-of-00008.safetensors", "model.vision.patch_embedding.proj.weight": "model-00006-of-00008.safetensors", "model.vision.pos_embed": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.0.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.1.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.10.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.11.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.12.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.13.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.14.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.15.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.16.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.17.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.18.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.19.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.2.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.22.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.22.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.22.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.22.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.22.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.3.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.30.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.4.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.4.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.40.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.48.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.49.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.5.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.5.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.50.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.50.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.51.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.52.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.53.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.54.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.56.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.mlp.fc2.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.mlp.fc2.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.post_attention_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.57.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.attention.dense.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.attention.dense.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.attention.query_key_value.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.attention.query_key_value.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.input_layernorm.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.mlp.fc1.bias": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.mlp.fc1.weight": "model-00007-of-00008.safetensors", "model.vision.transformer.layers.58.mlp.fc2.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.58.mlp.fc2.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.58.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.58.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.attention.dense.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.attention.dense.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.attention.query_key_value.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.input_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.mlp.fc1.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.mlp.fc1.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.mlp.fc2.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.mlp.fc2.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.59.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.6.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.6.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.60.attention.dense.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.attention.dense.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.attention.query_key_value.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.input_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.mlp.fc1.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.mlp.fc1.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.mlp.fc2.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.mlp.fc2.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.60.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.attention.dense.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.attention.dense.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.attention.query_key_value.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.input_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.mlp.fc1.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.mlp.fc1.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.mlp.fc2.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.mlp.fc2.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.61.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.attention.dense.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.attention.dense.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.attention.query_key_value.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.attention.query_key_value.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.input_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.mlp.fc1.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.mlp.fc1.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.mlp.fc2.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.mlp.fc2.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.post_attention_layernorm.bias": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.62.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.vision.transformer.layers.7.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.7.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.8.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.attention.dense.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.attention.dense.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.attention.query_key_value.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.attention.query_key_value.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.input_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.mlp.fc1.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.mlp.fc1.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.mlp.fc2.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.mlp.fc2.weight": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.post_attention_layernorm.bias": "model-00006-of-00008.safetensors", "model.vision.transformer.layers.9.post_attention_layernorm.weight": "model-00006-of-00008.safetensors" } }