Faro tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -17
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "<|
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -26,28 +26,12 @@
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
-
},
|
| 30 |
-
"6": {
|
| 31 |
-
"content": "<|im_start|>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": false
|
| 37 |
-
},
|
| 38 |
-
"7": {
|
| 39 |
-
"content": "<|im_end|>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": true
|
| 45 |
}
|
| 46 |
},
|
| 47 |
"bos_token": "<|startoftext|>",
|
| 48 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 49 |
"clean_up_tokenization_spaces": false,
|
| 50 |
-
"eos_token": "<|
|
| 51 |
"legacy": true,
|
| 52 |
"model_max_length": 4096,
|
| 53 |
"pad_token": "<unk>",
|
|
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
| 30 |
},
|
| 31 |
"bos_token": "<|startoftext|>",
|
| 32 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "<|endoftext|>",
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 4096,
|
| 37 |
"pad_token": "<unk>",
|