update chat_template and tokenizer_config.json to be compatible with transformers (#80)

- update (08bbcbdb905ecbc91ac04b53e9f548f38f028a3d)

chat_template.jinja

@@ -7,16 +7,13 @@
 {%- if not eos_token is defined -%}
     {%- set eos_token = "</s>" -%}
 {%- endif -%}
-{%- if not image_token is defined -%}
-    {%- set image_token = "<|IMAGE_START|><|IMAGE_PLACEHOLDER|><|IMAGE_END|>" -%}
-{%- endif -%}
 {{- cls_token -}}
 {%- for message in messages -%}
     {%- if message["role"] == "user" -%}
         {{- "User: " -}}
         {%- for content in message["content"] -%}
             {%- if content["type"] == "image" -%}
-                {{ image_token }}
+                {{ "<|IMAGE_START|><|IMAGE_PLACEHOLDER|><|IMAGE_END|>" }}
             {%- endif -%}
         {%- endfor -%}
         {%- for content in message["content"] -%}

config.json

@@ -68,6 +68,7 @@
     "torch_dtype": "bfloat16"
   },
   "vision_start_token_id": 101305,
+  "vision_end_token_id": 101306,
   "vocab_size": 103424,
   "weight_share_add_bias": true,
   "use_3d_rope": true,

tokenizer_config.json

@@ -8330,6 +8330,7 @@
   "clean_up_tokenization_spaces": false,
   "cls_token": "<|begin_of_sentence|>",
   "eos_token": "</s>",
+  "image_token": "<|IMAGE_PLACEHOLDER|>",
   "extra_special_tokens": {},
   "legacy": true,
   "mask_token": "<mask:1>",