minyichen commited on
Commit
c8da388
1 Parent(s): a2ab71e

Upload tokenizer_config.json

Browse files

The current chat_template adds an extra EOS token when `add_generation_prompt=False`.
Please replace it with the correct chat_template to fix this behavior.
```
from transformers import AutoTokenizer
message = [{"role": "user" , "content": 'How are you?'}]
tame_tokenizer = AutoTokenizer.from_pretrained('yentinglin/Llama-3-Taiwan-70B-Instruct')
tame_tokenizer.apply_chat_template(message , tokenize=False,add_generation_prompt=False)
```
You can see an extra EOS token in the output :
```
<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nHow are you?<|eot_id|><|eot_id|>
```

Files changed (1) hide show
  1. tokenizer_config.json +1 -2
tokenizer_config.json CHANGED
@@ -2050,7 +2050,7 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% else %}{{ eos_token }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
@@ -2058,6 +2058,5 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
2061
- "pad_token": "<|end_of_text|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }