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 +1,47 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|assistant|>": 151672,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endofassistant|>": 151673,
+  "<|endofimg|>": 151667,
+  "<|endofslice|>": 151682,
+  "<|endofsystemprompt|>": 151669,
+  "<|endoftext|>": 151643,
+  "<|endofuser|>": 151671,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_gen_end|>": 151687,
+  "<|image_gen_start|>": 151686,
+  "<|image_pad|>": 151655,
+  "<|imgpad|>": 151665,
+  "<|imgrowend|>": 151683,
+  "<|img|>": 151666,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|pictotext|>": 151679,
+  "<|pic|>": 151677,
+  "<|polygon_end|>": 151685,
+  "<|polygon_start|>": 151684,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|ref_end|>": 151675,
+  "<|ref_start|>": 151674,
+  "<|repo_name|>": 151663,
+  "<|slice|>": 151681,
+  "<|systemprompt|>": 151668,
+  "<|text|>": 151678,
+  "<|user|>": 151670,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652,
+  "[PAD]": 151680,
+  "[SEP]": 151676
+}

chat_template.json

@@ -1,3 +1,3 @@
 {
-    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{%- for m in messages %}{%- if m.role == 'system' %}{{- '<|system|>' + m.content + '<|endofsystem|>\n' }}{%- elif m.role == 'user' %}{% if m.content is string %}{{- '<|user|>' + m.content + '<|endofuser|>' }}{% else %} {% for content in m.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 %}<|img|><|imgpad|><|endofimg|>{% 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 %}<|img|><|video_pad|><|endofimg|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{%- endif %}{%- elif m.role == 'assistant' %}{{- '<|assistant|>' + m.content }}{%- if not loop.last %}{{- '<|endofassistant|>' }}{%- endif %}{%- endif %}{%- endfor %}{%- if messages[-1].role != 'assistant' %}{{- '<|assistant|>' }}{%- endif %}"
-}
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{%- for m in messages %}{%- if m.role == 'system' %}{{- '<|system|>' + m.content + '<|endofsystem|>\n' }}{%- elif m.role == 'user' %}{% if m.content is string %}{{- '<|user|>' + m.content + '<|endofuser|>' }}{% else %} {% for content in m.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 %}<|img|><|imgpad|><|endofimg|>{% 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 %}<|img|><|video_pad|><|endofimg|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{%- endif %}{%- elif m.role == 'assistant' %}{{- '<|assistant|>' + m.content }}{%- if not loop.last %}{{- '<|endofassistant|>' }}{%- endif %}{%- endif %}{%- endfor %}{%- if messages[-1].role != 'assistant' %}{{- '<|assistant|>' }}{%- endif %}"
+}

config.json

@@ -1,51 +1,54 @@
 {
-    "architectures": [
-        "DotsOCRForCausalLM"
-    ],
-    "model_type": "dots_ocr",
-    "auto_map": {
-        "AutoConfig": "configuration_dots.DotsOCRConfig",
-        "AutoModelForCausalLM": "modeling_dots_ocr.DotsOCRForCausalLM"
-        },
-    "attention_bias": true,
-    "attention_dropout": 0.0,
-    "hidden_act": "silu",
+  "architectures": [
+    "DotsOCRForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_dots.DotsOCRConfig",
+    "AutoModelForCausalLM": "modeling_dots_ocr.DotsOCRForCausalLM"
+  },
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151665,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "dots_ocr",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attn_implementation": "sdpa",
+    "embed_dim": 1536,
+    "gradient_checkpointing": false,
     "hidden_size": 1536,
+    "init_merger_std": 0.02,
     "initializer_range": 0.02,
-    "intermediate_size": 8960,
-    "max_position_embeddings": 131072,
-    "max_window_layers": 28,
+    "intermediate_size": 4224,
+    "is_causal": false,
+    "model_type": "dots_vit",
     "num_attention_heads": 12,
-    "num_hidden_layers": 28,
-    "num_key_value_heads": 2,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": null,
-    "rope_theta": 1000000,
-    "sliding_window": 131072,
-    "tie_word_embeddings": false,
-    "torch_dtype": "bfloat16",
-    "transformers_version": "4.51.0",
-    "use_cache": true,
-    "use_sliding_window": false,
-    "vocab_size": 151936,
-    "image_token_id": 151665,
-    "video_token_id": 151656,
-    "vision_config": {
-        "embed_dim": 1536,
-        "hidden_size": 1536,
-        "intermediate_size": 4224,
-        "num_hidden_layers": 42,
-        "num_attention_heads": 12,
-        "num_channels": 3,
-        "patch_size": 14,
-        "post_norm": true,
-        "rms_norm_eps": 1e-05,
-        "spatial_merge_size": 2,
-        "temporal_patch_size": 1,
-        "use_bias": false,
-        "attn_implementation": "flash_attention_2",
-        "init_merger_std": 0.02,
-        "initializer_range": 0.02,
-        "is_causal": false
-    }
-}
+    "num_channels": 3,
+    "num_hidden_layers": 42,
+    "patch_size": 14,
+    "post_norm": true,
+    "rms_norm_eps": 1e-05,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 1,
+    "use_bias": false
+  },
+  "vocab_size": 151936
+}

generation_config.json

@@ -1,7 +1,8 @@
 {
-  "max_length": 32768,
   "eos_token_id": [
     151643,
     151673
-  ]
+  ],
+  "max_length": 32768,
+  "transformers_version": "4.51.3"
 }

merges.txt

@@ -1,3 +1,4 @@
+#version: 0.2
 Ġ Ġ
 ĠĠ ĠĠ
 i n

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fbfb69fa1a560e66effca196a3b2d1219f86cb52f80d7b6bfb1f4e00a95312
+oid sha256:3f8cc38dae12107ee8633e42f7b8b96a8a7a8773714bc7aa04514ba02ecedbf7
 size 4988290528

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ed267205e54aa337865d635b10fb02cc427e6c56dd86097f008168bd51ef04
+oid sha256:10ad7ef4b15cde199c2b0ead551f9de126e2d39db93fc27e9bc23e8e05a710b4
 size 1090141200

model.safetensors.index.json

@@ -430,43 +430,43 @@
     "vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
     "vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
     "vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
-    "vision_tower.blocks.2.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.24.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.24.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.blocks.2.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
     "vision_tower.blocks.24.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.24.norm1.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
     "vision_tower.blocks.24.norm2.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.25.attn.proj.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.25.attn.qkv.weight": "model-00002-of-00002.safetensors",
@@ -503,13 +503,13 @@
     "vision_tower.blocks.29.mlp.fc3.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.29.norm1.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.29.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
     "vision_tower.blocks.30.attn.proj.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.30.attn.qkv.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
@@ -580,13 +580,13 @@
     "vision_tower.blocks.39.mlp.fc3.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.39.norm1.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.39.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
     "vision_tower.blocks.40.attn.proj.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.40.attn.qkv.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.40.mlp.fc1.weight": "model-00002-of-00002.safetensors",
@@ -601,50 +601,50 @@
     "vision_tower.blocks.41.mlp.fc3.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.41.norm1.weight": "model-00002-of-00002.safetensors",
     "vision_tower.blocks.41.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.mlp.fc3.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.mlp.fc3.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
     "vision_tower.merger.ln_q.bias": "model-00002-of-00002.safetensors",
     "vision_tower.merger.ln_q.weight": "model-00002-of-00002.safetensors",
     "vision_tower.merger.mlp.0.bias": "model-00002-of-00002.safetensors",
     "vision_tower.merger.mlp.0.weight": "model-00002-of-00002.safetensors",
     "vision_tower.merger.mlp.2.bias": "model-00002-of-00002.safetensors",
     "vision_tower.merger.mlp.2.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.patch_embed.patchifier.norm.weight": "model-00002-of-00002.safetensors",
-    "vision_tower.patch_embed.patchifier.proj.bias": "model-00002-of-00002.safetensors",
-    "vision_tower.patch_embed.patchifier.proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.patch_embed.patchifier.norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_embed.patchifier.proj.bias": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_embed.patchifier.proj.weight": "model-00001-of-00002.safetensors",
     "vision_tower.post_trunk_norm.weight": "model-00002-of-00002.safetensors"
   }
-}
+}

preprocessor_config.json

@@ -1,19 +1,29 @@
 {
-  "min_pixels": 3136,
-  "max_pixels": 11289600,
-  "patch_size": 14,
-  "temporal_patch_size": 1,
-  "merge_size": 2,
+  "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
   ],
-  "image_processor_type": "Qwen2VLImageProcessor",
-  "processor_class": "DotsVLProcessor"
+  "max_pixels": 11289600,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "DotsVLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 11289600,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 1
 }

special_tokens_map.json

@@ -21,5 +21,11 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "[PAD]"
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -383,8 +383,10 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "[PAD]",
+  "processor_class": "DotsVLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null