Upload processor

added_tokens.json

@@ -1,5 +1,6 @@
 {
   "<image>": 151646,
+  "<video>": 151647,
   "<|endoftext|>": 151643,
   "<|im_end|>": 151645,
   "<|im_start|>": 151644

chat_template.json

@@ -1,3 +1,3 @@
-{  
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
-}
+{
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+}

preprocessor_config.json

@@ -1,9 +1,4 @@
 {
-  "crop_size": {
-    "height": 384,
-    "width": 384
-  },
-  "do_center_crop": true,
   "do_convert_rgb": true,
   "do_normalize": true,
   "do_pad": true,
@@ -160,13 +155,13 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "LlavaNextImageProcessor",
+  "image_processor_type": "LlavaOnevisionImageProcessor",
   "image_std": [
     0.5,
     0.5,
     0.5
   ],
-  "processor_class": "LlavaNextProcessor",
+  "processor_class": "LlavaOnevisionProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {

processor_config.json

@@ -0,0 +1,8 @@
+{
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "image_token": "<image>",
+  "patch_size": 14,
+  "processor_class": "LlavaOnevisionProcessor",
+  "video_token": "<video>",
+  "vision_feature_select_strategy": "full"
+}

tokenizer.json

@@ -45,6 +45,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 151647,
+      "content": "<video>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -32,6 +32,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151647": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -45,7 +53,7 @@
   "errors": "replace",
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
-  "processor_class": "LlavaNextProcessor",
+  "processor_class": "LlavaOnevisionProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null