add video index

added_tokens.json

@@ -1,4 +1,5 @@
 {
   "<image>": 32001,
+  "<video>": 32002,
   "[PAD]": 32000
 }

config.json

@@ -44,6 +44,7 @@
   "torch_dtype": "float32",
   "transformers_version": "4.47.0.dev0",
   "use_decoder_only_language_model": true,
+  "video_token_index": 32002,
   "vision_config": {
     "_attn_implementation_autoset": true,
     "model_type": "instructblip_vision_model"

qformer_tokenizer/tokenizer_config.json

@@ -53,6 +53,7 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

tokenizer.json

@@ -47,6 +47,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32002,
+      "content": "<video>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -42,11 +42,20 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32002": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "</s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "legacy": true,
   "model_max_length": 2048,
   "pad_token": "[PAD]",