diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" new file mode 100644--- /dev/null +++ "b/model.safetensors.index.json" @@ -0,0 +1,1649 @@ +{ + "metadata": { + "total_size": 40371966608 + }, + "weight_map": { + "llm.lm_head.weight": "model-00009-of-00009.safetensors", + "llm.model.embed_tokens.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.modal_moes.point.down_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.modal_moes.point.gate_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.modal_moes.point.up_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.modal_moes.vision.down_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.modal_moes.vision.gate_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.modal_moes.vision.up_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.modal_moes.point.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.modal_moes.point.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.modal_moes.point.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.modal_moes.vision.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.modal_moes.vision.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.modal_moes.vision.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "llm.model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.modal_moes.point.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.modal_moes.point.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.modal_moes.point.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.modal_moes.vision.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.modal_moes.vision.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.modal_moes.vision.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.modal_moes.point.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.modal_moes.point.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.modal_moes.point.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.modal_moes.vision.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.modal_moes.vision.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.modal_moes.vision.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.modal_moes.point.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.12.modal_moes.point.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.modal_moes.point.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.12.modal_moes.vision.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.modal_moes.vision.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.modal_moes.vision.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.modal_moes.point.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.modal_moes.point.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.modal_moes.point.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.modal_moes.vision.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.modal_moes.vision.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.modal_moes.vision.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.modal_moes.point.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.modal_moes.point.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.modal_moes.point.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.modal_moes.vision.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.modal_moes.vision.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.modal_moes.vision.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.modal_moes.point.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.modal_moes.point.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.modal_moes.point.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.modal_moes.vision.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.modal_moes.vision.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.modal_moes.vision.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.modal_moes.point.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.16.modal_moes.point.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.16.modal_moes.point.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.16.modal_moes.vision.down_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.modal_moes.vision.gate_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.modal_moes.vision.up_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "llm.model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "llm.model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.modal_moes.point.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.modal_moes.point.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.modal_moes.point.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.modal_moes.vision.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.modal_moes.vision.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.modal_moes.vision.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.modal_moes.point.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.modal_moes.point.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.modal_moes.point.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.modal_moes.vision.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.modal_moes.vision.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.modal_moes.vision.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.input_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.modal_moes.point.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.modal_moes.point.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.modal_moes.point.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.modal_moes.vision.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.modal_moes.vision.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.modal_moes.vision.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.modal_moes.point.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.modal_moes.point.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.modal_moes.point.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.modal_moes.vision.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.modal_moes.vision.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.modal_moes.vision.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.modal_moes.point.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.20.modal_moes.point.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.20.modal_moes.point.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.20.modal_moes.vision.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.20.modal_moes.vision.gate_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.modal_moes.vision.up_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "llm.model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "llm.model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.modal_moes.point.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.modal_moes.point.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.modal_moes.point.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.modal_moes.vision.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.modal_moes.vision.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.modal_moes.vision.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.input_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.modal_moes.point.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.modal_moes.point.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.modal_moes.point.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.modal_moes.vision.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.modal_moes.vision.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.modal_moes.vision.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.input_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.modal_moes.point.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.modal_moes.point.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.modal_moes.point.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.modal_moes.vision.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.modal_moes.vision.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.modal_moes.vision.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.23.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.modal_moes.point.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.24.modal_moes.point.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.24.modal_moes.point.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.24.modal_moes.vision.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.24.modal_moes.vision.gate_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.modal_moes.vision.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "llm.model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "llm.model.layers.25.input_layernorm.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.modal_moes.point.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.modal_moes.point.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.modal_moes.point.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.modal_moes.vision.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.modal_moes.vision.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.modal_moes.vision.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.input_layernorm.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.modal_moes.point.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.modal_moes.point.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.modal_moes.point.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.modal_moes.vision.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.modal_moes.vision.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.modal_moes.vision.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.26.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.input_layernorm.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.modal_moes.point.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.modal_moes.point.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.modal_moes.point.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.modal_moes.vision.down_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.modal_moes.vision.gate_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.modal_moes.vision.up_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "llm.model.layers.27.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "llm.model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.modal_moes.point.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.modal_moes.point.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.modal_moes.point.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.modal_moes.vision.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.modal_moes.vision.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.modal_moes.vision.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.modal_moes.point.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.modal_moes.point.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.modal_moes.point.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.modal_moes.vision.down_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.modal_moes.vision.gate_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.modal_moes.vision.up_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.modal_moes.point.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.modal_moes.point.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.modal_moes.point.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.modal_moes.vision.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.modal_moes.vision.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.modal_moes.vision.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "llm.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "llm.model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.modal_moes.point.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.modal_moes.point.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.modal_moes.point.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.modal_moes.vision.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.modal_moes.vision.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.modal_moes.vision.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.modal_moes.point.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.modal_moes.point.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.modal_moes.point.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.modal_moes.vision.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.modal_moes.vision.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.modal_moes.vision.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.modal_moes.point.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.8.modal_moes.point.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.modal_moes.point.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.modal_moes.vision.down_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.modal_moes.vision.gate_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.modal_moes.vision.up_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "llm.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "llm.model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.modal_moes.point.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.modal_moes.point.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.modal_moes.point.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.modal_moes.vision.down_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.modal_moes.vision.gate_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.modal_moes.vision.up_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "llm.model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "llm.model.norm.weight": "model-00008-of-00009.safetensors", + "modal_embeds.point": "model-00009-of-00009.safetensors", + "modal_embeds.vision": "model-00009-of-00009.safetensors", + "modal_encoders.point.vision_tower.img_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.img_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.0.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.0.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.1.num_batches_tracked": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.1.running_mean": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.1.running_var": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.3.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.first_conv.3.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.0.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.0.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.1.num_batches_tracked": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.1.running_mean": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.1.running_var": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.3.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.embed.second_conv.3.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.0.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.1.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.10.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.11.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.12.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.13.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.14.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.15.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.16.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.17.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.18.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.19.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.2.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.20.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.21.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.22.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.23.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.3.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.4.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.5.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.6.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.7.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.8.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.attn.kv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.attn.kv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.attn.q.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.attn.q.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.global_blocks.9.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.0.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.1.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.10.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.11.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.12.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.13.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.14.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.15.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.16.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.17.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.18.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.19.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.2.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.20.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.21.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.22.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.23.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.3.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.4.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.5.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.6.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.7.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.8.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.attn.proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.attn.proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.attn.qkv.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.attn.qkv.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.blocks.local_blocks.9.norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.ln_f1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.ln_f1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.ln_f2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.encoder.ln_f2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.global_query": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.norm.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.norm.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.pos_embed.0.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.pos_embed.0.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.pos_embed.2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.model.pos_embed.2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.text_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.point.vision_tower.text_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.embeddings.position_embedding.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.attention.in_proj_bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.attention.in_proj_weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.attention.out_proj.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.attention.out_proj.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.layernorm.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.layernorm.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.mlp.fc1.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.mlp.fc1.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.mlp.fc2.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.mlp.fc2.weight": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.head.probe": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.post_layernorm.bias": "model-00001-of-00009.safetensors", + "modal_encoders.vision.vision_model.post_layernorm.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj1.0.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj1.0.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj1.2.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj1.2.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj1.4.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj1.4.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj2.0.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj2.0.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj2.2.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj2.2.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj2.4.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj2.4.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj3.0.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj3.0.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj3.2.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj3.2.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj3.4.bias": "model-00001-of-00009.safetensors", + "modal_projectors.point.proj3.4.weight": "model-00001-of-00009.safetensors", + "modal_projectors.point.prompt1": "model-00001-of-00009.safetensors", + "modal_projectors.point.prompt2": "model-00001-of-00009.safetensors", + "modal_projectors.point.prompt3": "model-00001-of-00009.safetensors", + "modal_projectors.vision.module.0.bias": "model-00001-of-00009.safetensors", + "modal_projectors.vision.module.0.weight": "model-00001-of-00009.safetensors", + "modal_projectors.vision.module.2.bias": "model-00001-of-00009.safetensors", + "modal_projectors.vision.module.2.weight": "model-00001-of-00009.safetensors", + "modal_projectors.vision.module.4.bias": "model-00001-of-00009.safetensors", + "modal_projectors.vision.module.4.weight": "model-00001-of-00009.safetensors", + "modal_projectors.vision.resample_pad_token": "model-00001-of-00009.safetensors" + } +}