Upload processor

chat_template.jinja

@@ -17,15 +17,13 @@ You are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help
         {{- message['content'] -}}
     {% else %}
         {% for content in message['content'] %}
-            {% if content is string %}
-                {{- content -}}
-            {% elif content['type'] == 'text' or 'text' in content %}
+            {% if content['type'] == 'text' %}
                 {{- content['text'] -}}
-            {% elif content['type'] == 'image' or 'image' in content %}
-                {{- image_token + '
+            {% elif content['type'] == 'image' %}
+                {{- '<|image_pad|>' + '
 ' -}}
-            {% elif content['type'] == 'video' or 'video' in content %}
-                {{- video_token + '
+            {% elif content['type'] == 'video' %}
+                {{- '<|video_pad|>' + '
 ' -}}
             {% endif %}
         {% endfor %}

preprocessor_config.json

@@ -8,18 +8,24 @@
     0.5,
     0.5
   ],
-  "image_merge_size": 1,
   "image_processor_type": "Videollama3ImageProcessor",
   "image_std": [
     0.5,
     0.5,
     0.5
   ],
+  "max_pixels": 3211264,
   "max_tokens": 16384,
+  "merge_size": 1,
+  "min_pixels": 3136,
   "min_tokens": 16,
   "patch_size": 14,
   "processor_class": "Videollama3Processor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
-  "video_merge_size": 1
+  "size": {
+    "longest_edge": 1003520,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 1
 }

video_preprocessor_config.json

@@ -9,14 +9,13 @@
   "do_pad": null,
   "do_rescale": true,
   "do_resize": true,
-  "do_sample_frames": true,
+  "do_sample_frames": false,
   "fps": null,
   "image_mean": [
     0.5,
     0.5,
     0.5
   ],
-  "image_merge_size": null,
   "image_std": [
     0.5,
     0.5,
@@ -24,16 +23,21 @@
   ],
   "input_data_format": null,
   "max_frames": 180,
-  "max_tokens": 16384,
-  "min_tokens": 16,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 12544,
   "num_frames": null,
   "patch_size": 14,
   "processor_class": "Videollama3Processor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
-  "size": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 12544
+  },
   "size_divisor": null,
-  "video_merge_size": 2,
+  "temporal_patch_size": 1,
   "video_metadata": null,
   "video_processor_type": "Videollama3VideoProcessor"
 }