Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +17 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": "<|im_start|>",
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"unk_token": "<|endoftext|>",
|
| 7 |
+
"pad_token": "<|endoftext|>",
|
| 8 |
+
"tokenizer_class": "MiniCPMOTokenizerFast",
|
| 9 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
|
| 10 |
+
"model_max_length": 32768,
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoTokenizer": [
|
| 13 |
+
"tokenization_minicpmo_fast.MiniCPMOTokenizerFast",
|
| 14 |
+
null
|
| 15 |
+
]
|
| 16 |
+
}
|
| 17 |
+
}
|