Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "architectures": [
+    "ColQwen2"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62474ec6098fb1ba40753f2c11bdafbbce36131cead0a926268bb245a13bb2a
+size 4966659944

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7581ed4420a86ccbbc6718835012ac2f35b6db7abffa207dc95c334d62ace7
+size 4991495816

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b903a4bb3d4771d0536e715f22de56af4d57a369b5226542a012c2b1fc3cec68
+size 4932751040

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1252ea8e878e53f9b5e1028fbc476cad770c1db5911c90a1c0ac1aa154fd20
+size 1692842312

model.safetensors.index.json

@@ -0,0 +1,739 @@
+{
+  "metadata": {
+    "total_size": 16583668992
+  },
+  "weight_map": {
+    "custom_text_proj.bias": "model-00004-of-00004.safetensors",
+    "custom_text_proj.weight": "model-00004-of-00004.safetensors",
+    "lm_head.weight": "model-00004-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-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-00002-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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-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-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "ColQwen2Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

results.json

@@ -0,0 +1,582 @@
+{
+    "vidore/arxivqa_test_subsampled": {
+        "ndcg_at_1": 0.87,
+        "ndcg_at_3": 0.89971,
+        "ndcg_at_5": 0.9146,
+        "ndcg_at_10": 0.92076,
+        "ndcg_at_20": 0.9232,
+        "ndcg_at_50": 0.92445,
+        "ndcg_at_100": 0.92575,
+        "map_at_1": 0.87,
+        "map_at_3": 0.89267,
+        "map_at_5": 0.90097,
+        "map_at_10": 0.9037,
+        "map_at_20": 0.90433,
+        "map_at_50": 0.90455,
+        "map_at_100": 0.90467,
+        "recall_at_1": 0.87,
+        "recall_at_3": 0.92,
+        "recall_at_5": 0.956,
+        "recall_at_10": 0.974,
+        "recall_at_20": 0.984,
+        "recall_at_50": 0.99,
+        "recall_at_100": 0.998,
+        "precision_at_1": 0.87,
+        "precision_at_3": 0.30667,
+        "precision_at_5": 0.1912,
+        "precision_at_10": 0.0974,
+        "precision_at_20": 0.0492,
+        "precision_at_50": 0.0198,
+        "precision_at_100": 0.00998,
+        "mrr_at_1": 0.868,
+        "mrr_at_3": 0.8926666666666665,
+        "mrr_at_5": 0.9010666666666663,
+        "mrr_at_10": 0.9032333333333331,
+        "mrr_at_20": 0.9038726836888601,
+        "mrr_at_50": 0.9040981863343626,
+        "mrr_at_100": 0.9042154113217136,
+        "naucs_at_1_max": 0.7759016514848549,
+        "naucs_at_1_std": -0.07636080870917564,
+        "naucs_at_1_diff1": 0.9178701029400873,
+        "naucs_at_3_max": 0.7505018674136326,
+        "naucs_at_3_std": -0.0976540616246483,
+        "naucs_at_3_diff1": 0.9075630252100865,
+        "naucs_at_5_max": 0.7691409897292251,
+        "naucs_at_5_std": -0.17152618623206986,
+        "naucs_at_5_diff1": 0.913844325609031,
+        "naucs_at_10_max": 0.8861595920419414,
+        "naucs_at_10_std": -0.07297277885513653,
+        "naucs_at_10_diff1": 0.9484665661136262,
+        "naucs_at_20_max": 0.9115896358543447,
+        "naucs_at_20_std": 0.19193510737628516,
+        "naucs_at_20_diff1": 0.9325980392156931,
+        "naucs_at_50_max": 0.947712418300658,
+        "naucs_at_50_std": 0.010924369747883845,
+        "naucs_at_50_diff1": 0.9738562091503188,
+        "naucs_at_100_max": 1.0,
+        "naucs_at_100_std": 1.0,
+        "naucs_at_100_diff1": 1.0
+    },
+    "vidore/docvqa_test_subsampled": {
+        "ndcg_at_1": 0.55654,
+        "ndcg_at_3": 0.62285,
+        "ndcg_at_5": 0.64298,
+        "ndcg_at_10": 0.65674,
+        "ndcg_at_20": 0.6708,
+        "ndcg_at_50": 0.68247,
+        "ndcg_at_100": 0.69013,
+        "map_at_1": 0.55654,
+        "map_at_3": 0.60532,
+        "map_at_5": 0.61652,
+        "map_at_10": 0.62227,
+        "map_at_20": 0.62616,
+        "map_at_50": 0.62813,
+        "map_at_100": 0.62883,
+        "recall_at_1": 0.55654,
+        "recall_at_3": 0.67406,
+        "recall_at_5": 0.72284,
+        "recall_at_10": 0.76497,
+        "recall_at_20": 0.8204,
+        "recall_at_50": 0.87805,
+        "recall_at_100": 0.92461,
+        "precision_at_1": 0.55654,
+        "precision_at_3": 0.22469,
+        "precision_at_5": 0.14457,
+        "precision_at_10": 0.0765,
+        "precision_at_20": 0.04102,
+        "precision_at_50": 0.01756,
+        "precision_at_100": 0.00925,
+        "mrr_at_1": 0.5543237250554324,
+        "mrr_at_3": 0.6056910569105692,
+        "mrr_at_5": 0.6163340724316333,
+        "mrr_at_10": 0.6222565375004397,
+        "mrr_at_20": 0.6263930444590208,
+        "mrr_at_50": 0.6281533502118082,
+        "mrr_at_100": 0.6288252316605568,
+        "naucs_at_1_max": 0.497847351531617,
+        "naucs_at_1_std": -0.33814500917634066,
+        "naucs_at_1_diff1": 0.8645836037088763,
+        "naucs_at_3_max": 0.4701480123071679,
+        "naucs_at_3_std": -0.34741402449178754,
+        "naucs_at_3_diff1": 0.816322894093004,
+        "naucs_at_5_max": 0.4347871177259376,
+        "naucs_at_5_std": -0.3602860416064191,
+        "naucs_at_5_diff1": 0.7758571855344005,
+        "naucs_at_10_max": 0.45324296482414395,
+        "naucs_at_10_std": -0.34596987897850606,
+        "naucs_at_10_diff1": 0.7544028038035664,
+        "naucs_at_20_max": 0.4086941718861015,
+        "naucs_at_20_std": -0.24939767166193863,
+        "naucs_at_20_diff1": 0.7174109964559481,
+        "naucs_at_50_max": 0.4052361174628584,
+        "naucs_at_50_std": -0.12921981686486492,
+        "naucs_at_50_diff1": 0.7068264858128372,
+        "naucs_at_100_max": 0.4303274261407769,
+        "naucs_at_100_std": 0.1893856757251087,
+        "naucs_at_100_diff1": 0.7510538837895515
+    },
+    "vidore/infovqa_test_subsampled": {
+        "ndcg_at_1": 0.88664,
+        "ndcg_at_3": 0.91724,
+        "ndcg_at_5": 0.92561,
+        "ndcg_at_10": 0.92884,
+        "ndcg_at_20": 0.93091,
+        "ndcg_at_50": 0.93251,
+        "ndcg_at_100": 0.93353,
+        "map_at_1": 0.88664,
+        "map_at_3": 0.91026,
+        "map_at_5": 0.91491,
+        "map_at_10": 0.91622,
+        "map_at_20": 0.9168,
+        "map_at_50": 0.91706,
+        "map_at_100": 0.91715,
+        "recall_at_1": 0.88664,
+        "recall_at_3": 0.93725,
+        "recall_at_5": 0.95749,
+        "recall_at_10": 0.96761,
+        "recall_at_20": 0.97571,
+        "recall_at_50": 0.98381,
+        "recall_at_100": 0.98988,
+        "precision_at_1": 0.88664,
+        "precision_at_3": 0.31242,
+        "precision_at_5": 0.1915,
+        "precision_at_10": 0.09676,
+        "precision_at_20": 0.04879,
+        "precision_at_50": 0.01968,
+        "precision_at_100": 0.0099,
+        "mrr_at_1": 0.8846153846153846,
+        "mrr_at_3": 0.9095816464237515,
+        "mrr_at_5": 0.9137314439946017,
+        "mrr_at_10": 0.9150022492127753,
+        "mrr_at_20": 0.9156172230591575,
+        "mrr_at_50": 0.9158740133336603,
+        "mrr_at_100": 0.9159712069854167,
+        "naucs_at_1_max": 0.6570420185225749,
+        "naucs_at_1_std": 0.021742422508079725,
+        "naucs_at_1_diff1": 0.9406199945564582,
+        "naucs_at_3_max": 0.6318777024153259,
+        "naucs_at_3_std": -0.13867851955525243,
+        "naucs_at_3_diff1": 0.9166153687134068,
+        "naucs_at_5_max": 0.7688027815053647,
+        "naucs_at_5_std": 0.12215100872667127,
+        "naucs_at_5_diff1": 0.908003985735216,
+        "naucs_at_10_max": 0.7611694369997123,
+        "naucs_at_10_std": 0.2568374691733195,
+        "naucs_at_10_diff1": 0.8966136523873394,
+        "naucs_at_20_max": 0.9302075684869188,
+        "naucs_at_20_std": 0.5376863638154207,
+        "naucs_at_20_diff1": 0.9224381659931805,
+        "naucs_at_50_max": 0.9116365344884687,
+        "naucs_at_50_std": 0.5788807451893666,
+        "naucs_at_50_diff1": 0.9346992729676175,
+        "naucs_at_100_max": 0.8847387459944923,
+        "naucs_at_100_std": 0.5437597991332108,
+        "naucs_at_100_diff1": 0.9477594183740937
+    },
+    "vidore/tabfquad_test_subsampled": {
+        "ndcg_at_1": 0.93571,
+        "ndcg_at_3": 0.95459,
+        "ndcg_at_5": 0.96059,
+        "ndcg_at_10": 0.96527,
+        "ndcg_at_20": 0.96527,
+        "ndcg_at_50": 0.96527,
+        "ndcg_at_100": 0.96589,
+        "map_at_1": 0.93571,
+        "map_at_3": 0.95,
+        "map_at_5": 0.95339,
+        "map_at_10": 0.95537,
+        "map_at_20": 0.95537,
+        "map_at_50": 0.95537,
+        "map_at_100": 0.95543,
+        "recall_at_1": 0.93571,
+        "recall_at_3": 0.96786,
+        "recall_at_5": 0.98214,
+        "recall_at_10": 0.99643,
+        "recall_at_20": 0.99643,
+        "recall_at_50": 0.99643,
+        "recall_at_100": 1.0,
+        "precision_at_1": 0.93571,
+        "precision_at_3": 0.32262,
+        "precision_at_5": 0.19643,
+        "precision_at_10": 0.09964,
+        "precision_at_20": 0.04982,
+        "precision_at_50": 0.01993,
+        "precision_at_100": 0.01,
+        "mrr_at_1": 0.9357142857142857,
+        "mrr_at_3": 0.9511904761904761,
+        "mrr_at_5": 0.9535119047619046,
+        "mrr_at_10": 0.955484693877551,
+        "mrr_at_20": 0.955484693877551,
+        "mrr_at_50": 0.955484693877551,
+        "mrr_at_100": 0.955548469387755,
+        "naucs_at_1_max": 0.5400197115883385,
+        "naucs_at_1_std": -0.014264965245358233,
+        "naucs_at_1_diff1": 0.9125946674966273,
+        "naucs_at_3_max": 0.71428571428571,
+        "naucs_at_3_std": 0.3626932254383213,
+        "naucs_at_3_diff1": 0.9110384894698589,
+        "naucs_at_5_max": 0.8245564892623743,
+        "naucs_at_5_std": 0.3671335200747002,
+        "naucs_at_5_diff1": 0.9183006535947714,
+        "naucs_at_10_max": 1.0,
+        "naucs_at_10_std": 1.0,
+        "naucs_at_10_diff1": 0.8692810457516478,
+        "naucs_at_20_max": 1.0,
+        "naucs_at_20_std": 1.0,
+        "naucs_at_20_diff1": 0.8692810457516478,
+        "naucs_at_50_max": 1.0,
+        "naucs_at_50_std": 1.0,
+        "naucs_at_50_diff1": 0.8692810457515607,
+        "naucs_at_100_max": 1.0,
+        "naucs_at_100_std": 1.0,
+        "naucs_at_100_diff1": 1.0
+    },
+    "vidore/tatdqa_test": {
+        "ndcg_at_1": 0.66464,
+        "ndcg_at_3": 0.76743,
+        "ndcg_at_5": 0.78563,
+        "ndcg_at_10": 0.80598,
+        "ndcg_at_20": 0.81164,
+        "ndcg_at_50": 0.8141,
+        "ndcg_at_100": 0.81571,
+        "map_at_1": 0.66464,
+        "map_at_3": 0.74281,
+        "map_at_5": 0.75302,
+        "map_at_10": 0.7616,
+        "map_at_20": 0.76322,
+        "map_at_50": 0.76363,
+        "map_at_100": 0.76379,
+        "recall_at_1": 0.66464,
+        "recall_at_3": 0.8384,
+        "recall_at_5": 0.88214,
+        "recall_at_10": 0.94411,
+        "recall_at_20": 0.96598,
+        "recall_at_50": 0.97813,
+        "recall_at_100": 0.98785,
+        "precision_at_1": 0.66464,
+        "precision_at_3": 0.27947,
+        "precision_at_5": 0.17643,
+        "precision_at_10": 0.09441,
+        "precision_at_20": 0.0483,
+        "precision_at_50": 0.01956,
+        "precision_at_100": 0.00988,
+        "mrr_at_1": 0.6682867557715675,
+        "mrr_at_3": 0.7444309437019037,
+        "mrr_at_5": 0.7550931551235324,
+        "mrr_at_10": 0.7633802001967253,
+        "mrr_at_20": 0.7649268100771701,
+        "mrr_at_50": 0.7653640518991484,
+        "mrr_at_100": 0.7655149926790836,
+        "naucs_at_1_max": 0.1850885816800905,
+        "naucs_at_1_std": -0.28841580839611636,
+        "naucs_at_1_diff1": 0.8092207194564194,
+        "naucs_at_3_max": 0.22777444593854884,
+        "naucs_at_3_std": -0.19766587895858276,
+        "naucs_at_3_diff1": 0.6835545302979953,
+        "naucs_at_5_max": 0.24718915870776953,
+        "naucs_at_5_std": -0.20386104103344074,
+        "naucs_at_5_diff1": 0.6717631348394746,
+        "naucs_at_10_max": 0.4129645887196616,
+        "naucs_at_10_std": 0.08874265042732231,
+        "naucs_at_10_diff1": 0.6599246442060299,
+        "naucs_at_20_max": 0.36324695580118865,
+        "naucs_at_20_std": 0.25905536406088486,
+        "naucs_at_20_diff1": 0.661930000003523,
+        "naucs_at_50_max": 0.4870532250141124,
+        "naucs_at_50_std": 0.42734413587689424,
+        "naucs_at_50_diff1": 0.6936991113088404,
+        "naucs_at_100_max": 0.6138710077391127,
+        "naucs_at_100_std": 0.610321256875322,
+        "naucs_at_100_diff1": 0.6717110238397306
+    },
+    "vidore/shiftproject_test": {
+        "ndcg_at_1": 0.75,
+        "ndcg_at_3": 0.86702,
+        "ndcg_at_5": 0.87906,
+        "ndcg_at_10": 0.88207,
+        "ndcg_at_20": 0.88207,
+        "ndcg_at_50": 0.88207,
+        "ndcg_at_100": 0.88362,
+        "map_at_1": 0.75,
+        "map_at_3": 0.83833,
+        "map_at_5": 0.84483,
+        "map_at_10": 0.84594,
+        "map_at_20": 0.84594,
+        "map_at_50": 0.84594,
+        "map_at_100": 0.84606,
+        "recall_at_1": 0.75,
+        "recall_at_3": 0.95,
+        "recall_at_5": 0.98,
+        "recall_at_10": 0.99,
+        "recall_at_20": 0.99,
+        "recall_at_50": 0.99,
+        "recall_at_100": 1.0,
+        "precision_at_1": 0.75,
+        "precision_at_3": 0.31667,
+        "precision_at_5": 0.196,
+        "precision_at_10": 0.099,
+        "precision_at_20": 0.0495,
+        "precision_at_50": 0.0198,
+        "precision_at_100": 0.01,
+        "mrr_at_1": 0.77,
+        "mrr_at_3": 0.8516666666666667,
+        "mrr_at_5": 0.8586666666666666,
+        "mrr_at_10": 0.8597777777777778,
+        "mrr_at_20": 0.8597777777777778,
+        "mrr_at_50": 0.8597777777777778,
+        "mrr_at_100": 0.8598954248366013,
+        "naucs_at_1_max": 0.1504761904761907,
+        "naucs_at_1_std": -0.2593406593406595,
+        "naucs_at_1_diff1": 0.84887493458922,
+        "naucs_at_3_max": 0.4772175536881391,
+        "naucs_at_3_std": 0.00018674136321205462,
+        "naucs_at_3_diff1": 0.7637721755368763,
+        "naucs_at_5_max": 0.540149393090577,
+        "naucs_at_5_std": 0.1914098972922579,
+        "naucs_at_5_diff1": 0.9346405228758136,
+        "naucs_at_10_max": 0.7222222222222276,
+        "naucs_at_10_std": 0.5541549953314738,
+        "naucs_at_10_diff1": 0.8692810457516413,
+        "naucs_at_20_max": 0.7222222222222276,
+        "naucs_at_20_std": 0.5541549953314738,
+        "naucs_at_20_diff1": 0.8692810457516413,
+        "naucs_at_50_max": 0.7222222222222041,
+        "naucs_at_50_std": 0.554154995331464,
+        "naucs_at_50_diff1": 0.8692810457516374,
+        "naucs_at_100_max": null,
+        "naucs_at_100_std": null,
+        "naucs_at_100_diff1": null
+    },
+    "vidore/syntheticDocQA_artificial_intelligence_test": {
+        "ndcg_at_1": 0.99,
+        "ndcg_at_3": 0.99631,
+        "ndcg_at_5": 0.99631,
+        "ndcg_at_10": 0.99631,
+        "ndcg_at_20": 0.99631,
+        "ndcg_at_50": 0.99631,
+        "ndcg_at_100": 0.99631,
+        "map_at_1": 0.99,
+        "map_at_3": 0.995,
+        "map_at_5": 0.995,
+        "map_at_10": 0.995,
+        "map_at_20": 0.995,
+        "map_at_50": 0.995,
+        "map_at_100": 0.995,
+        "recall_at_1": 0.99,
+        "recall_at_3": 1.0,
+        "recall_at_5": 1.0,
+        "recall_at_10": 1.0,
+        "recall_at_20": 1.0,
+        "recall_at_50": 1.0,
+        "recall_at_100": 1.0,
+        "precision_at_1": 0.99,
+        "precision_at_3": 0.33333,
+        "precision_at_5": 0.2,
+        "precision_at_10": 0.1,
+        "precision_at_20": 0.05,
+        "precision_at_50": 0.02,
+        "precision_at_100": 0.01,
+        "mrr_at_1": 0.99,
+        "mrr_at_3": 0.995,
+        "mrr_at_5": 0.995,
+        "mrr_at_10": 0.995,
+        "mrr_at_20": 0.995,
+        "mrr_at_50": 0.995,
+        "mrr_at_100": 0.995,
+        "naucs_at_1_max": 0.12278244631185359,
+        "naucs_at_1_std": 0.12278244631185359,
+        "naucs_at_1_diff1": 1.0,
+        "naucs_at_3_max": 1.0,
+        "naucs_at_3_std": 1.0,
+        "naucs_at_3_diff1": 1.0,
+        "naucs_at_5_max": 1.0,
+        "naucs_at_5_std": 1.0,
+        "naucs_at_5_diff1": 1.0,
+        "naucs_at_10_max": 1.0,
+        "naucs_at_10_std": 1.0,
+        "naucs_at_10_diff1": 1.0,
+        "naucs_at_20_max": 1.0,
+        "naucs_at_20_std": 1.0,
+        "naucs_at_20_diff1": 1.0,
+        "naucs_at_50_max": null,
+        "naucs_at_50_std": null,
+        "naucs_at_50_diff1": null,
+        "naucs_at_100_max": null,
+        "naucs_at_100_std": null,
+        "naucs_at_100_diff1": null
+    },
+    "vidore/syntheticDocQA_energy_test": {
+        "ndcg_at_1": 0.93,
+        "ndcg_at_3": 0.94893,
+        "ndcg_at_5": 0.95323,
+        "ndcg_at_10": 0.95972,
+        "ndcg_at_20": 0.95972,
+        "ndcg_at_50": 0.96159,
+        "ndcg_at_100": 0.96159,
+        "map_at_1": 0.93,
+        "map_at_3": 0.945,
+        "map_at_5": 0.9475,
+        "map_at_10": 0.95018,
+        "map_at_20": 0.95018,
+        "map_at_50": 0.95043,
+        "map_at_100": 0.95043,
+        "recall_at_1": 0.93,
+        "recall_at_3": 0.96,
+        "recall_at_5": 0.97,
+        "recall_at_10": 0.99,
+        "recall_at_20": 0.99,
+        "recall_at_50": 1.0,
+        "recall_at_100": 1.0,
+        "precision_at_1": 0.93,
+        "precision_at_3": 0.32,
+        "precision_at_5": 0.194,
+        "precision_at_10": 0.099,
+        "precision_at_20": 0.0495,
+        "precision_at_50": 0.02,
+        "precision_at_100": 0.01,
+        "mrr_at_1": 0.94,
+        "mrr_at_3": 0.95,
+        "mrr_at_5": 0.9545,
+        "mrr_at_10": 0.9561666666666667,
+        "mrr_at_20": 0.9561666666666667,
+        "mrr_at_50": 0.9564298245614035,
+        "mrr_at_100": 0.9564298245614035,
+        "naucs_at_1_max": 0.30052020808323304,
+        "naucs_at_1_std": -0.6699346405228773,
+        "naucs_at_1_diff1": 0.9813258636788056,
+        "naucs_at_3_max": 0.7864145658263298,
+        "naucs_at_3_std": -0.6272175536881414,
+        "naucs_at_3_diff1": 1.0,
+        "naucs_at_5_max": 0.7587924058512269,
+        "naucs_at_5_std": -1.0210084033613454,
+        "naucs_at_5_diff1": 1.0,
+        "naucs_at_10_max": 0.7222222222222276,
+        "naucs_at_10_std": -1.1517273576097316,
+        "naucs_at_10_diff1": 1.0,
+        "naucs_at_20_max": 0.7222222222222276,
+        "naucs_at_20_std": -1.1517273576097316,
+        "naucs_at_20_diff1": 1.0,
+        "naucs_at_50_max": null,
+        "naucs_at_50_std": null,
+        "naucs_at_50_diff1": null,
+        "naucs_at_100_max": null,
+        "naucs_at_100_std": null,
+        "naucs_at_100_diff1": null
+    },
+    "vidore/syntheticDocQA_government_reports_test": {
+        "ndcg_at_1": 0.91,
+        "ndcg_at_3": 0.94655,
+        "ndcg_at_5": 0.95947,
+        "ndcg_at_10": 0.95947,
+        "ndcg_at_20": 0.95947,
+        "ndcg_at_50": 0.95947,
+        "ndcg_at_100": 0.95947,
+        "map_at_1": 0.91,
+        "map_at_3": 0.93833,
+        "map_at_5": 0.94583,
+        "map_at_10": 0.94583,
+        "map_at_20": 0.94583,
+        "map_at_50": 0.94583,
+        "map_at_100": 0.94583,
+        "recall_at_1": 0.91,
+        "recall_at_3": 0.97,
+        "recall_at_5": 1.0,
+        "recall_at_10": 1.0,
+        "recall_at_20": 1.0,
+        "recall_at_50": 1.0,
+        "recall_at_100": 1.0,
+        "precision_at_1": 0.91,
+        "precision_at_3": 0.32333,
+        "precision_at_5": 0.2,
+        "precision_at_10": 0.1,
+        "precision_at_20": 0.05,
+        "precision_at_50": 0.02,
+        "precision_at_100": 0.01,
+        "mrr_at_1": 0.93,
+        "mrr_at_3": 0.955,
+        "mrr_at_5": 0.9575,
+        "mrr_at_10": 0.9575,
+        "mrr_at_20": 0.9575,
+        "mrr_at_50": 0.9575,
+        "mrr_at_100": 0.9575,
+        "naucs_at_1_max": 0.6442577030812321,
+        "naucs_at_1_std": 0.19950202303143538,
+        "naucs_at_1_diff1": 0.8887332710862121,
+        "naucs_at_3_max": 0.807812013694371,
+        "naucs_at_3_std": 0.3029878618113896,
+        "naucs_at_3_diff1": 0.9074074074074082,
+        "naucs_at_5_max": 1.0,
+        "naucs_at_5_std": 1.0,
+        "naucs_at_5_diff1": 1.0,
+        "naucs_at_10_max": 1.0,
+        "naucs_at_10_std": 1.0,
+        "naucs_at_10_diff1": 1.0,
+        "naucs_at_20_max": 1.0,
+        "naucs_at_20_std": 1.0,
+        "naucs_at_20_diff1": 1.0,
+        "naucs_at_50_max": null,
+        "naucs_at_50_std": null,
+        "naucs_at_50_diff1": null,
+        "naucs_at_100_max": null,
+        "naucs_at_100_std": null,
+        "naucs_at_100_diff1": null
+    },
+    "vidore/syntheticDocQA_healthcare_industry_test": {
+        "ndcg_at_1": 0.99,
+        "ndcg_at_3": 0.99631,
+        "ndcg_at_5": 0.99631,
+        "ndcg_at_10": 0.99631,
+        "ndcg_at_20": 0.99631,
+        "ndcg_at_50": 0.99631,
+        "ndcg_at_100": 0.99631,
+        "map_at_1": 0.99,
+        "map_at_3": 0.995,
+        "map_at_5": 0.995,
+        "map_at_10": 0.995,
+        "map_at_20": 0.995,
+        "map_at_50": 0.995,
+        "map_at_100": 0.995,
+        "recall_at_1": 0.99,
+        "recall_at_3": 1.0,
+        "recall_at_5": 1.0,
+        "recall_at_10": 1.0,
+        "recall_at_20": 1.0,
+        "recall_at_50": 1.0,
+        "recall_at_100": 1.0,
+        "precision_at_1": 0.99,
+        "precision_at_3": 0.33333,
+        "precision_at_5": 0.2,
+        "precision_at_10": 0.1,
+        "precision_at_20": 0.05,
+        "precision_at_50": 0.02,
+        "precision_at_100": 0.01,
+        "mrr_at_1": 0.99,
+        "mrr_at_3": 0.995,
+        "mrr_at_5": 0.995,
+        "mrr_at_10": 0.995,
+        "mrr_at_20": 0.995,
+        "mrr_at_50": 0.995,
+        "mrr_at_100": 0.995,
+        "naucs_at_1_max": 0.554154995331463,
+        "naucs_at_1_std": 0.7222222222222201,
+        "naucs_at_1_diff1": 0.8692810457516276,
+        "naucs_at_3_max": 1.0,
+        "naucs_at_3_std": 1.0,
+        "naucs_at_3_diff1": 1.0,
+        "naucs_at_5_max": 1.0,
+        "naucs_at_5_std": 1.0,
+        "naucs_at_5_diff1": 1.0,
+        "naucs_at_10_max": 1.0,
+        "naucs_at_10_std": 1.0,
+        "naucs_at_10_diff1": 1.0,
+        "naucs_at_20_max": 1.0,
+        "naucs_at_20_std": 1.0,
+        "naucs_at_20_diff1": 1.0,
+        "naucs_at_50_max": null,
+        "naucs_at_50_std": null,
+        "naucs_at_50_diff1": null,
+        "naucs_at_100_max": null,
+        "naucs_at_100_std": null,
+        "naucs_at_100_diff1": null
+    }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "ColQwen2Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}