Commit ·
544b080
1
Parent(s): cac413b
Upload tokenizer
Browse files- tokenizer_config.json +4 -3
tokenizer_config.json
CHANGED
|
@@ -28,9 +28,9 @@
|
|
| 28 |
},
|
| 29 |
"32000": {
|
| 30 |
"content": "<|pad|>",
|
| 31 |
-
"lstrip":
|
| 32 |
"normalized": false,
|
| 33 |
-
"rstrip":
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
| 36 |
}
|
|
@@ -41,6 +41,7 @@
|
|
| 41 |
"</s>"
|
| 42 |
],
|
| 43 |
"bos_token": "<s>",
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"eos_token": "</s>",
|
| 46 |
"legacy": true,
|
|
@@ -50,7 +51,7 @@
|
|
| 50 |
"sp_model_kwargs": {},
|
| 51 |
"spaces_between_special_tokens": false,
|
| 52 |
"tokenizer_class": "LlamaTokenizer",
|
| 53 |
-
"tokenizer_file": "/home/nonroot/.cache/
|
| 54 |
"unk_token": "<unk>",
|
| 55 |
"use_default_system_prompt": true
|
| 56 |
}
|
|
|
|
| 28 |
},
|
| 29 |
"32000": {
|
| 30 |
"content": "<|pad|>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
"normalized": false,
|
| 33 |
+
"rstrip": true,
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
| 36 |
}
|
|
|
|
| 41 |
"</s>"
|
| 42 |
],
|
| 43 |
"bos_token": "<s>",
|
| 44 |
+
"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 %}",
|
| 45 |
"clean_up_tokenization_spaces": false,
|
| 46 |
"eos_token": "</s>",
|
| 47 |
"legacy": true,
|
|
|
|
| 51 |
"sp_model_kwargs": {},
|
| 52 |
"spaces_between_special_tokens": false,
|
| 53 |
"tokenizer_class": "LlamaTokenizer",
|
| 54 |
+
"tokenizer_file": "/home/nonroot/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/5e9c98b96d071dce59368012254c55b0ec6f8658/tokenizer.json",
|
| 55 |
"unk_token": "<unk>",
|
| 56 |
"use_default_system_prompt": true
|
| 57 |
}
|