Upload folder using huggingface_hub

llava-med3_CXR/config.json

@@ -0,0 +1,193 @@
+{
+  "_name_or_path": "/vast/users/xiaodan/haokunlin/Continual_LLaVA/llava/output/llava-v1.5-7b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dataset_type": "llava-med",
+  "dataset_type_map": {
+    "dataset": {
+      "GQA": [
+        24,
+        32
+      ],
+      "Grounding": [
+        40,
+        48
+      ],
+      "ImageNet": [
+        16,
+        24
+      ],
+      "OCRVQA": [
+        56,
+        64
+      ],
+      "ScienceQA": [
+        0,
+        8
+      ],
+      "TextVQA": [
+        8,
+        16
+      ],
+      "VQAv2": [
+        48,
+        56
+      ],
+      "VizWiz": [
+        32,
+        40
+      ]
+    },
+    "domain": {
+      "chartqa": [
+        0,
+        8
+      ],
+      "docvqa": [
+        8,
+        16
+      ],
+      "iconqa": [
+        16,
+        24
+      ],
+      "medicalqa": [
+        24,
+        32
+      ]
+    },
+    "llava-med": {
+      "CT": [
+        8,
+        16
+      ],
+      "CXR": [
+        0,
+        8
+      ],
+      "MRI": [
+        16,
+        24
+      ]
+    },
+    "newdomain": {
+      "GeoChat_Instruct": [
+        0,
+        8
+      ],
+      "agri": [
+        40,
+        48
+      ],
+      "art": [
+        24,
+        32
+      ],
+      "astro": [
+        32,
+        40
+      ],
+      "atom": [
+        16,
+        24
+      ],
+      "chem": [
+        48,
+        56
+      ],
+      "climate": [
+        56,
+        64
+      ],
+      "llava_med": [
+        8,
+        16
+      ]
+    },
+    "vqa_rad": {
+      "abd": [
+        0,
+        8
+      ],
+      "chest": [
+        8,
+        16
+      ],
+      "head": [
+        16,
+        24
+      ]
+    }
+  },
+  "disable_task_id": false,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "groups": 4,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "low_rank": 8,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "/vast/users/xiaodan/haokunlin/Continual_LLaVA/llava/output/clip-vit-large-patch14-336",
+  "model_name": "/vast/users/xiaodan/haokunlin/Continual_LLaVA/llava/output/llava-v1.5-7b",
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pool_size": 24,
+  "pool_train_keys": true,
+  "pool_train_weights": true,
+  "preprare_retreival_version": "firstq",
+  "pretraining_tp": 1,
+  "random_dropout": null,
+  "retriever_state_dict": "/vast/users/xiaodan/haokunlin/Continual_LLaVA/llava/output/prompt-key/merged_prompt_key3.pth",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "similarity_type": "cosine",
+  "task": "CXR",
+  "task_pool_index_range": {
+    "CT": [
+      8,
+      16
+    ],
+    "CXR": [
+      0,
+      8
+    ],
+    "MRI": [
+      16,
+      24
+    ]
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000,
+  "weight_topk": 4
+}

llava-med3_CXR/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

llava-med3_CXR/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0249d255cd0d67de360b4a1f578904b0baeea9c9b326a6818c2248f856c35d0
+size 4938985352

llava-med3_CXR/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216448014a22b547b66308b4d8b5a1e21ccd2e5aa1a4500a204d645df9c3eddd
+size 4947390880

llava-med3_CXR/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf0886cf9cb7a352f36e5a6156a416a50df6870ebaa4ffcc8b79d02a99ceffd
+size 4998097112

llava-med3_CXR/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5f4934798ccd451eeaf8ee25d4eb2d989ac806e01a9b8e30bdc75958b4ada1
+size 268469384

llava-med3_CXR/model.safetensors.index.json

@@ -0,0 +1,916 @@
+{
+  "metadata": {
+    "total_size": 15152818688
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00003-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00003-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.embeddings.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.embeddings.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.embeddings.position_embeddings.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.embeddings.token_type_embeddings.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.embeddings.word_embeddings.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.0.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.1.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.10.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.11.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.2.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.3.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.4.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.5.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.6.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.7.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.8.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.self.key.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.self.key.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.self.query.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.self.query.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.self.value.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.attention.self.value.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.intermediate.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.intermediate.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.output.LayerNorm.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.output.LayerNorm.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.output.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.encoder.layer.9.output.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.bert.pooler.dense.bias": "model-00003-of-00004.safetensors",
+    "retriever.bert.pooler.dense.weight": "model-00003-of-00004.safetensors",
+    "retriever.cross_attn.in_proj_bias": "model-00004-of-00004.safetensors",
+    "retriever.cross_attn.in_proj_weight": "model-00004-of-00004.safetensors",
+    "retriever.cross_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "retriever.cross_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "retriever.cross_key_proj.weight": "model-00003-of-00004.safetensors",
+    "retriever.cross_out_proj.weight": "model-00004-of-00004.safetensors",
+    "retriever.cross_query_proj.weight": "model-00003-of-00004.safetensors",
+    "retriever.cross_value_proj.weight": "model-00004-of-00004.safetensors",
+    "retriever.current_weight": "model-00003-of-00004.safetensors",
+    "retriever.hyper_U.0.bias": "model-00003-of-00004.safetensors",
+    "retriever.hyper_U.0.weight": "model-00003-of-00004.safetensors",
+    "retriever.hyper_U.2.bias": "model-00003-of-00004.safetensors",
+    "retriever.hyper_U.2.weight": "model-00003-of-00004.safetensors",
+    "retriever.hyper_V": "model-00003-of-00004.safetensors",
+    "retriever.keys": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.0": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.1": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.2": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.3": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.4": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.5": "model-00003-of-00004.safetensors",
+    "retriever.previous_weights.6": "model-00003-of-00004.safetensors",
+    "retriever.retrieve_lora": "model-00003-of-00004.safetensors",
+    "retriever.weight_offset_components": "model-00003-of-00004.safetensors"
+  }
+}

llava-med3_CXR/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llava-med3_CXR/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

llava-med3_CXR/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

llava-med3_CXR/trainer_state.json

@@ -0,0 +1,798 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 0.9504,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 0.901,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8892,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.8945,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9996790752964305e-05,
+      "loss": 0.9304,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998716507171053e-05,
+      "loss": 0.8248,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9971129134476474e-05,
+      "loss": 0.8799,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 0.8107,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.991987177050743e-05,
+      "loss": 0.814,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9884683243281117e-05,
+      "loss": 0.8273,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9843150237975343e-05,
+      "loss": 0.7225,
+      "step": 11
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9795299412524948e-05,
+      "loss": 0.7666,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9741161479953872e-05,
+      "loss": 0.7477,
+      "step": 13
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9680771188662044e-05,
+      "loss": 0.8081,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9614167300122126e-05,
+      "loss": 0.7169,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.954139256400049e-05,
+      "loss": 0.7017,
+      "step": 16
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9462493690718373e-05,
+      "loss": 0.748,
+      "step": 17
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9377521321470806e-05,
+      "loss": 0.74,
+      "step": 18
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9286529995722624e-05,
+      "loss": 0.7023,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.918957811620231e-05,
+      "loss": 0.7195,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.908672791141625e-05,
+      "loss": 0.7492,
+      "step": 21
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.897804539570742e-05,
+      "loss": 0.7827,
+      "step": 22
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8863600326884085e-05,
+      "loss": 0.7626,
+      "step": 23
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8743466161445823e-05,
+      "loss": 0.6308,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8617720007435497e-05,
+      "loss": 0.7193,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.848644257494751e-05,
+      "loss": 0.7459,
+      "step": 26
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8349718124324075e-05,
+      "loss": 0.7188,
+      "step": 27
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 0.6928,
+      "step": 28
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8060282634540053e-05,
+      "loss": 0.6785,
+      "step": 29
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7907757369376984e-05,
+      "loss": 0.7021,
+      "step": 30
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.775015651483459e-05,
+      "loss": 0.728,
+      "step": 31
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.758758122692791e-05,
+      "loss": 0.7852,
+      "step": 32
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.742013585450911e-05,
+      "loss": 0.7506,
+      "step": 33
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.72479278722912e-05,
+      "loss": 0.7215,
+      "step": 34
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.6616,
+      "step": 35
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.688966919075687e-05,
+      "loss": 0.7027,
+      "step": 36
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6703848439562787e-05,
+      "loss": 0.6649,
+      "step": 37
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6513724827222225e-05,
+      "loss": 0.6965,
+      "step": 38
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.631942038446304e-05,
+      "loss": 0.7633,
+      "step": 39
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.612105982547663e-05,
+      "loss": 0.7032,
+      "step": 40
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5918770467870174e-05,
+      "loss": 0.7299,
+      "step": 41
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5712682150947926e-05,
+      "loss": 0.7497,
+      "step": 42
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5502927152373913e-05,
+      "loss": 0.6567,
+      "step": 43
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5289640103269626e-05,
+      "loss": 0.7845,
+      "step": 44
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5072957901801075e-05,
+      "loss": 0.6851,
+      "step": 45
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4853019625310813e-05,
+      "loss": 1.1505,
+      "step": 46
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4629966441051208e-05,
+      "loss": 0.6876,
+      "step": 47
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 0.724,
+      "step": 48
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4175089922850633e-05,
+      "loss": 0.6419,
+      "step": 49
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3943558551133186e-05,
+      "loss": 0.6427,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.370949600869768e-05,
+      "loss": 0.6889,
+      "step": 51
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3473052528448203e-05,
+      "loss": 0.6133,
+      "step": 52
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3234379871492381e-05,
+      "loss": 0.7282,
+      "step": 53
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2993631229733584e-05,
+      "loss": 0.664,
+      "step": 54
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2750961127544782e-05,
+      "loss": 0.7104,
+      "step": 55
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2506525322587207e-05,
+      "loss": 0.687,
+      "step": 56
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.226048070583735e-05,
+      "loss": 0.7036,
+      "step": 57
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2012985200886602e-05,
+      "loss": 0.6427,
+      "step": 58
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1764197662578087e-05,
+      "loss": 0.6852,
+      "step": 59
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1514277775045768e-05,
+      "loss": 0.6511,
+      "step": 60
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1263385949221294e-05,
+      "loss": 0.6968,
+      "step": 61
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1011683219874324e-05,
+      "loss": 0.6419,
+      "step": 62
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0759331142252463e-05,
+      "loss": 0.7007,
+      "step": 63
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0506491688387128e-05,
+      "loss": 0.6628,
+      "step": 64
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.025332714313188e-05,
+      "loss": 0.6848,
+      "step": 65
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.6743,
+      "step": 66
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.746672856868124e-06,
+      "loss": 0.7049,
+      "step": 67
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 0.7198,
+      "step": 68
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.24066885774754e-06,
+      "loss": 0.6612,
+      "step": 69
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.98831678012568e-06,
+      "loss": 0.6872,
+      "step": 70
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.73661405077871e-06,
+      "loss": 0.729,
+      "step": 71
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.485722224954237e-06,
+      "loss": 0.6582,
+      "step": 72
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.23580233742192e-06,
+      "loss": 0.6372,
+      "step": 73
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.987014799113398e-06,
+      "loss": 0.6753,
+      "step": 74
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.739519294162652e-06,
+      "loss": 0.6639,
+      "step": 75
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.493474677412795e-06,
+      "loss": 0.7035,
+      "step": 76
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.24903887245522e-06,
+      "loss": 0.6967,
+      "step": 77
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.006368770266421e-06,
+      "loss": 0.6869,
+      "step": 78
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.7656201285076195e-06,
+      "loss": 0.621,
+      "step": 79
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.526947471551799e-06,
+      "loss": 0.7983,
+      "step": 80
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.290503991302324e-06,
+      "loss": 0.7536,
+      "step": 81
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.056441448866817e-06,
+      "loss": 0.7016,
+      "step": 82
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.824910077149372e-06,
+      "loss": 0.7122,
+      "step": 83
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.5960584844236565e-06,
+      "loss": 0.6673,
+      "step": 84
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.370033558948793e-06,
+      "loss": 0.6829,
+      "step": 85
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.146980374689192e-06,
+      "loss": 0.6367,
+      "step": 86
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.9270420981989295e-06,
+      "loss": 0.6852,
+      "step": 87
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 0.7771,
+      "step": 88
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.497072847626087e-06,
+      "loss": 0.6214,
+      "step": 89
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.287317849052075e-06,
+      "loss": 0.7045,
+      "step": 90
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.081229532129826e-06,
+      "loss": 0.6388,
+      "step": 91
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.878940174523371e-06,
+      "loss": 0.6837,
+      "step": 92
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.680579615536961e-06,
+      "loss": 0.6438,
+      "step": 93
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.48627517277778e-06,
+      "loss": 0.7031,
+      "step": 94
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.296151560437214e-06,
+      "loss": 0.6787,
+      "step": 95
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.110330809243134e-06,
+      "loss": 0.6887,
+      "step": 96
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.6507,
+      "step": 97
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7520721277088023e-06,
+      "loss": 0.6693,
+      "step": 98
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5798641454908945e-06,
+      "loss": 0.6592,
+      "step": 99
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4124187730720916e-06,
+      "loss": 0.6302,
+      "step": 100
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2498434851654125e-06,
+      "loss": 0.6973,
+      "step": 101
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.092242630623016e-06,
+      "loss": 0.7026,
+      "step": 102
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.939717365459952e-06,
+      "loss": 0.6599,
+      "step": 103
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7923655879272395e-06,
+      "loss": 0.6968,
+      "step": 104
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6502818756759275e-06,
+      "loss": 0.6881,
+      "step": 105
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5135574250524898e-06,
+      "loss": 0.6795,
+      "step": 106
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3822799925645036e-06,
+      "loss": 0.6798,
+      "step": 107
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 0.5719,
+      "step": 108
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1363996731159188e-06,
+      "loss": 0.6188,
+      "step": 109
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0219546042925842e-06,
+      "loss": 0.6073,
+      "step": 110
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.132720885837509e-07,
+      "loss": 0.6661,
+      "step": 111
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.10421883797694e-07,
+      "loss": 0.7008,
+      "step": 112
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.13470004277379e-07,
+      "loss": 0.6657,
+      "step": 113
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.22478678529197e-07,
+      "loss": 0.6355,
+      "step": 114
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.375063092816313e-07,
+      "loss": 0.7221,
+      "step": 115
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.5860743599951186e-07,
+      "loss": 0.674,
+      "step": 116
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.8583269987787607e-07,
+      "loss": 0.6352,
+      "step": 117
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1922881133795827e-07,
+      "loss": 0.6568,
+      "step": 118
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.588385200461307e-07,
+      "loss": 0.5833,
+      "step": 119
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0470058747505516e-07,
+      "loss": 0.6403,
+      "step": 120
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5684976202465786e-07,
+      "loss": 0.601,
+      "step": 121
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1531675671888621e-07,
+      "loss": 0.6923,
+      "step": 122
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.012822949256981e-08,
+      "loss": 0.7158,
+      "step": 123
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.1306766081048456e-08,
+      "loss": 0.6602,
+      "step": 124
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.8870865523525916e-08,
+      "loss": 0.5667,
+      "step": 125
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2834928289472415e-08,
+      "loss": 0.6606,
+      "step": 126
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.209247035694807e-09,
+      "loss": 0.6622,
+      "step": 127
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.73,
+      "step": 128
+    },
+    {
+      "epoch": 1.0,
+      "step": 128,
+      "total_flos": 7094238343168.0,
+      "train_loss": 0.7066151765175164,
+      "train_runtime": 322.5111,
+      "train_samples_per_second": 12.676,
+      "train_steps_per_second": 0.397
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 128,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 7094238343168.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

llava-med3_CXR/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbbbf263b9ce65aec6baa43ce4bd441c6892d289ada43d269941dbbb4219e2a
+size 7249