model.safetensors.index.json

{
  "metadata": {
    "total_size": 6219562240
  },
  "weight_map": {
    "lm_head.weight": "model-00002-of-00002.safetensors",
    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
    "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
    "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
    "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
    "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
    "model.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.clip_decoder.0.head.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.clip_decoder.0.head.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.clip_decoder.0.norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.clip_decoder.0.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.cls_token": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.0.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.1.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.10.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.11.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.12.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.13.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.14.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.15.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.16.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.17.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.18.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.19.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.2.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.20.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.21.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.22.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.23.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.24.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.25.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.26.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.27.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.28.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.29.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.3.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.30.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.31.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.4.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.5.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.6.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.7.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.8.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.A_b_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.A_log": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.D": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.D_b": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.conv1d_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.conv1d_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.dt_proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.dt_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.dt_proj_b.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.dt_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.x_proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.mixer.x_proj_b.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.layers.9.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.pool_norm.bias": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.pool_norm.weight": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.pos_embed": "model-00002-of-00002.safetensors",
    "model.vision_tower.vision_tower.vision_encoder.temporal_pos_embedding": "model-00002-of-00002.safetensors"
  }
}