Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -146,6 +146,7 @@
|
|
| 146 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 147 |
"clean_up_tokenization_spaces": false,
|
| 148 |
"eos_token": "<|im_end|>",
|
|
|
|
| 149 |
"model_max_length": 2048,
|
| 150 |
"pad_token": "<|im_end|>",
|
| 151 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
| 146 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 147 |
"clean_up_tokenization_spaces": false,
|
| 148 |
"eos_token": "<|im_end|>",
|
| 149 |
+
"extra_special_tokens": {},
|
| 150 |
"model_max_length": 2048,
|
| 151 |
"pad_token": "<|im_end|>",
|
| 152 |
"tokenizer_class": "GPT2Tokenizer",
|