Upload folder using huggingface_hub

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set point_cloud_count = namespace(value=0) %}\n{%- set point_cloud_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif content.type == 'point_cloud' or 'point_cloud' in content %}\n                    {%- set point_cloud_count.value = point_cloud_count.value + 1 %}\n                    {%- if add_vision_id %}Point Cloud {{ point_cloud_count.value }}: {% endif -%}\n                    <|point_cloud_start|><|point_cloud_pad|><|point_cloud_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif content.type == 'point_cloud' or 'point_cloud' in content %}\n                    {%- set point_cloud_count.value = point_cloud_count.value + 1 %}\n                    {%- if add_vision_id %}Point Cloud {{ point_cloud_count.value }}: {% endif -%}\n                    <|point_cloud_start|><|point_cloud_pad|><|point_cloud_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -2,74 +2,13 @@
   "architectures": [
     "Qwen3VLForConditionalGeneration"
   ],
-  "bg_token_id": 151673,
-  "ce_loss_threshold": 0.05,
-  "decoder_mode": "joint",
-  "dtype": "float32",
-  "eos_token_id": 151645,
   "image_token_id": 151655,
-  "mask_decoder_config": {
-    "decoder_chunk_size": 8,
-    "dtype": "float32",
-    "mask_decoder_embedding_input_dim": 2560,
-    "mask_decoder_transformer_dim": 512,
-    "model_type": "qwen3_vl_mask_decoder",
-    "transformer_attention_downsample_rate": 2,
-    "transformer_depth": 2,
-    "transformer_embedding_dim": 512,
-    "transformer_mlp_dim": 2048,
-    "transformer_num_heads": 8,
-    "utonia_enc_channels": [
-      54,
-      108,
-      216,
-      432,
-      576
-    ]
-  },
-  "mask_decoder_fusion_mode": "concat",
   "model_type": "qwen3_vl",
-  "pad_token_id": 151643,
-  "point_cloud_config": {
-    "ckpt_path": null,
-    "downsample_ratio": 20,
-    "drop_path_rate": 0.0,
-    "dtype": "float32",
-    "embed_dim": 64,
-    "geo_decoder_downsample_ratio": 1,
-    "geo_decoder_ln_post": true,
-    "geo_decoder_mlp_expand_ratio": 4,
-    "heads": 16,
-    "include_pi": false,
-    "label_type": "binary",
-    "model_type": "qwen3_vl_point_cloud",
-    "num_decoder_layers": 16,
-    "num_encoder_layers": 8,
-    "num_freqs": 8,
-    "num_latents": 4096,
-    "output_hidden_size": 2560,
-    "pc_sharpedge_size": 0,
-    "pc_size": 81920,
-    "point_feats": 4,
-    "qk_norm": true,
-    "qkv_bias": false,
-    "scale_factor": 1.0039506158752403,
-    "surface_extractor": null,
-    "use_ln_post": true,
-    "volume_decoder": null,
-    "width": 1024
-  },
-  "point_cloud_encoder_type": "utonia",
-  "point_cloud_end_token_id": 151670,
-  "point_cloud_start_token_id": 151669,
-  "point_cloud_token_id": 151671,
-  "seg_loss_weight": 1.0,
-  "seg_token_id": 151672,
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
-    "dtype": "float32",
+    "dtype": "bfloat16",
     "eos_token_id": 151645,
     "head_dim": 128,
     "hidden_act": "silu",
@@ -97,18 +36,7 @@
     "vocab_size": 151936
   },
   "tie_word_embeddings": true,
-  "transformers_version": "4.57.3",
-  "use_mask_decoder": true,
-  "utonia_ckpt_path": "/vinowan-cfs/zhezhu/code/verl/third_party/Utonia/ckpt/utonia.pth",
-  "utonia_enc_channels": [
-    54,
-    108,
-    216,
-    432,
-    576
-  ],
-  "utonia_num_tokens": 4096,
-  "utonia_scale": 5.0,
+  "transformers_version": "4.57.0.dev0",
   "video_token_id": 151656,
   "vision_config": {
     "deepstack_visual_indexes": [
@@ -117,7 +45,6 @@
       17
     ],
     "depth": 24,
-    "dtype": "float32",
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1024,
     "in_channels": 3,
@@ -131,6 +58,66 @@
     "spatial_merge_size": 2,
     "temporal_patch_size": 2
   },
+  "point_cloud_config": {
+    "model_type": "qwen3_vl_point_cloud",
+    "attn_implementation": "flash_attention_2",
+    "num_latents": 4096,
+    "embed_dim": 64,
+    "width": 1024,
+    "heads": 16,
+    "num_encoder_layers": 8,
+    "num_decoder_layers": 16,
+    "qkv_bias": false,
+    "qk_norm": true,
+    "scale_factor": 1.0039506158752403,
+    "geo_decoder_mlp_expand_ratio": 4,
+    "num_freqs": 8,
+    "include_pi": false,
+    "point_feats": 4,
+    "pc_size": 81920,
+    "pc_sharpedge_size": 0,
+    "geo_decoder_downsample_ratio": 1,
+    "geo_decoder_ln_post": true,
+    "output_hidden_size": 2560
+  },
   "vision_end_token_id": 151653,
-  "vision_start_token_id": 151652
-}
+  "vision_start_token_id": 151652,
+  "point_cloud_token_id": 151671,
+  "point_cloud_end_token_id": 151670,
+  "point_cloud_start_token_id": 151669,
+  "seg_loss_weight": 1.0,
+  "ce_loss_threshold": 0.05,
+  "seg_token_id": 151672,
+  "bg_token_id": 151673,
+  "decoder_mode": "joint",
+  "use_mask_decoder": true,
+  "point_cloud_encoder_type": "utonia",
+  "utonia_ckpt_path": "/vinowan-cfs/zhezhu/code/verl/third_party/Utonia/ckpt/utonia.pth",
+  "utonia_scale": 5.0,
+  "utonia_num_tokens": 4096,
+  "utonia_enc_channels": [
+    54,
+    108,
+    216,
+    432,
+    576
+  ],
+  "mask_decoder_config": {
+    "model_type": "qwen3_vl_mask_decoder",
+    "transformer_depth": 2,
+    "transformer_embedding_dim": 512,
+    "transformer_num_heads": 8,
+    "transformer_mlp_dim": 2048,
+    "transformer_attention_downsample_rate": 2,
+    "mask_decoder_transformer_dim": 512,
+    "mask_decoder_embedding_input_dim": 2560,
+    "utonia_enc_channels": [
+      54,
+      108,
+      216,
+      432,
+      576
+    ],
+    "decoder_chunk_size": 8
+  }
+}

generation_config.json

@@ -1,13 +1,14 @@
 {
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.57.3"
-}
+    "bos_token_id": 151643,
+    "pad_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "top_k": 20,
+    "top_p": 0.8,
+    "repetition_penalty": 1.0,
+    "temperature": 0.7,
+    "transformers_version": "4.56.0"
+}

merges.txt

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

preprocessor_config.json

@@ -1,39 +1,21 @@
 {
-  "crop_size": null,
-  "data_format": "channels_first",
-  "default_to_square": true,
-  "device": null,
-  "disable_grouping": null,
-  "do_center_crop": null,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_pad": null,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "Qwen2VLImageProcessorFast",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "input_data_format": null,
-  "max_pixels": null,
-  "merge_size": 2,
-  "min_pixels": null,
-  "pad_size": null,
-  "patch_size": 16,
-  "processor_class": "Qwen3VLProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "return_tensors": null,
-  "size": {
-    "longest_edge": 16777216,
-    "shortest_edge": 65536
-  },
-  "temporal_patch_size": 2
-}
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer_config.json

@@ -272,13 +272,12 @@
     "<|BG|>"
   ],
   "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- set point_cloud_count = namespace(value=0) %}\n{%- set point_cloud_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif content.type == 'point_cloud' or 'point_cloud' in content %}\n                    {%- set point_cloud_count.value = point_cloud_count.value + 1 %}\n                    {%- if add_vision_id %}Point Cloud {{ point_cloud_count.value }}: {% endif -%}\n                    <|point_cloud_start|><|point_cloud_pad|><|point_cloud_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif content.type == 'point_cloud' or 'point_cloud' in content %}\n                    {%- set point_cloud_count.value = point_cloud_count.value + 1 %}\n                    {%- if add_vision_id %}Point Cloud {{ point_cloud_count.value }}: {% endif -%}\n                    <|point_cloud_start|><|point_cloud_pad|><|point_cloud_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
-  "processor_class": "Qwen3VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

video_preprocessor_config.json

@@ -1,41 +1,21 @@
 {
-  "crop_size": null,
-  "data_format": "channels_first",
-  "default_to_square": true,
-  "device": null,
-  "do_center_crop": null,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "do_sample_frames": true,
-  "fps": 2,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "input_data_format": null,
-  "max_frames": 768,
-  "merge_size": 2,
-  "min_frames": 4,
-  "num_frames": null,
-  "pad_size": null,
-  "patch_size": 16,
-  "processor_class": "Qwen3VLProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "return_metadata": false,
-  "size": {
-    "longest_edge": 25165824,
-    "shortest_edge": 4096
-  },
-  "temporal_patch_size": 2,
-  "video_metadata": null,
-  "video_processor_type": "Qwen3VLVideoProcessor"
-}
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}