update tokenizer

README.md

@@ -59,7 +59,7 @@ tags:
 pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
 pip install flash-attn --no-build-isolation
 
-# For better performance, you can install grouped-gemm, which may take 3-5 minutes to install
+# For better inference performance, you can install grouped-gemm, which may take 3-5 minutes to install
 pip install grouped_gemm==0.1.6
 ```
 

added_tokens.json

@@ -1,4 +0,0 @@
-{
- "</s>": 100353,
- "<s>": 100352
-}

special_tokens_map.json

@@ -1,18 +1,4 @@
 {
- "bos_token": {
- "content": "<s>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
- "eos_token": {
- "content": "</s>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false
- },
  "unk_token": {
  "content": "<unk>",
  "lstrip": false,

tokenizer_config.json

@@ -10,28 +10,12 @@
  "rstrip": false,
  "single_word": false,
  "special": true
- },
- "100352": {
- "content": "<s>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "100353": {
- "content": "</s>",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
  }
  },
- "bos_token": "<s>",
+ "bos_token": null,
  "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 %}",
  "clean_up_tokenization_spaces": false,
- "eos_token": "</s>",
+ "eos_token": null,
  "legacy": true,
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": null,