m-ric HF staff commited on
Commit
d5d3ba6
1 Parent(s): 9f3e00e

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer_config.json +5 -1
special_tokens_map.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "pad_token": {
3
  "content": "<pad>",
4
  "lstrip": false,
 
1
  {
2
+ "image_token": "<|img|>",
3
  "pad_token": {
4
  "content": "<pad>",
5
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -4944,7 +4944,11 @@
4944
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
4945
  "clean_up_tokenization_spaces": false,
4946
  "eos_token": null,
4947
- "extra_special_tokens": {},
 
 
 
 
4948
  "legacy": true,
4949
  "model_max_length": 1000000000000000019884624838656,
4950
  "pad_token": "<pad>",
 
4944
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
4945
  "clean_up_tokenization_spaces": false,
4946
  "eos_token": null,
4947
+ "extra_special_tokens": {
4948
+ "image_token": "<|img|>",
4949
+ "pad_token": "<pad>"
4950
+ },
4951
+ "image_token": "<|img|>",
4952
  "legacy": true,
4953
  "model_max_length": 1000000000000000019884624838656,
4954
  "pad_token": "<pad>",