Upload processor

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n    {% if message['role'] == 'stream' %}\n        {% set identifier = 'stream' %}\n    {% else %}\n        {% set identifier = 'im' %}\n    {% endif %}\n    {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n    {% if message['content'] is string %}\n        {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n    {% else %}\n        {% for content in message['content'] %}\n            {% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}\n                {% if 'time' in content %}\n                    {{- 'Time ' + content['time'] | round(1) | string + 's: ' -}}\n                {% endif %}\n\n                {{- '<image>\n' -}}\n\n            {% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}\n                {% for i in range(content['num_frames']) %}\n                    {% if 'timestamps' in content %}\n                        {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n                    {% endif %}\n                    {% if i < content['num_frames'] - 1 %}\n\n                        {{- '<image>,' -}}\n\n                    {% else %}\n\n                        {{- '<image>\n' -}}\n\n                    {% endif %}\n                {% endfor %}\n            {% elif content['type'] == 'text' or 'text' in content %}\n                {{- content['text'] -}}\n            {% endif %}\n        {% endfor %}\n        {{- '<|' + identifier + '_end|>\n' -}}\n    {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n"
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "DAMO-NLP-SG/SigLIP-NaViT--image_processing_videollama3.Videollama3ImageProcessor"
+  },
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Videollama3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "max_tokens": 16384,
+  "min_tokens": 16,
+  "patch_size": 14,
+  "processor_class": "Videollama3Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098
+}

tokenizer_config.json

@@ -229,7 +229,7 @@
   "model_max_length": 16384,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
-  "processor_class": "Videollama3Qwen2Processor",
+  "processor_class": "Videollama3Processor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null