Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +6 -6
tokenizer_config.json
CHANGED
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
-
"normalized":
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
-
"normalized":
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
@@ -44,13 +44,13 @@
|
|
| 44 |
}
|
| 45 |
},
|
| 46 |
"additional_special_tokens": [
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
],
|
| 50 |
-
"bos_token": "
|
| 51 |
"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 %}",
|
| 52 |
"clean_up_tokenization_spaces": false,
|
| 53 |
-
"eos_token": "
|
| 54 |
"model_max_length": 4096,
|
| 55 |
"pad_token": null,
|
| 56 |
"sp_model_kwargs": {},
|
|
|
|
| 13 |
"1": {
|
| 14 |
"content": "<s>",
|
| 15 |
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false,
|
| 19 |
"special": true
|
|
|
|
| 21 |
"2": {
|
| 22 |
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
| 44 |
}
|
| 45 |
},
|
| 46 |
"additional_special_tokens": [
|
| 47 |
+
"<s>",
|
| 48 |
+
"</s>"
|
| 49 |
],
|
| 50 |
+
"bos_token": "<|im_start|>",
|
| 51 |
"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 %}",
|
| 52 |
"clean_up_tokenization_spaces": false,
|
| 53 |
+
"eos_token": "<|im_end|>",
|
| 54 |
"model_max_length": 4096,
|
| 55 |
"pad_token": null,
|
| 56 |
"sp_model_kwargs": {},
|