Upload processor

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>\n' }}{% elif content['type'] == 'video' %}{{ '<video>\n' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>\n'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}"
+}

preprocessor_config.json

@@ -18,6 +18,7 @@
   ],
   "max_patches": 12,
   "min_patches": 1,
+  "processor_class": "InternVLProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "InternVLProcessor"
+}

special_tokens_map.json

@@ -13,69 +13,15 @@
     "<|vision_pad|>",
     "<|image_pad|>",
     "<|video_pad|>",
-    {
-      "content": "<img>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</img>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<IMG_CONTEXT>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<quad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</quad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<ref>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</ref>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<box>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "</box>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
   ],
   "eos_token": {
     "content": "<|im_end|>",

tokenizer_config.json

@@ -283,6 +283,7 @@
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<|endoftext|>",
+  "processor_class": "InternVLProcessor",
   "return_token_type_ids": false,
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",