Update tokenizer_config.json
Browse files- tokenizer_config.json +3 -37
tokenizer_config.json
CHANGED
|
@@ -1,46 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<unk>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<s>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"2": {
|
| 21 |
-
"content": "</s>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"3": {
|
| 29 |
-
"content": "<pad>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
}
|
| 36 |
-
},
|
| 37 |
"bos_token": "<s>",
|
| 38 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' and loop.first %}{{ '### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'user' %}{{ '\n### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'assistant' %}{{ '\n### Trả lời: ' + message['content'] + eos_token }}{% endif %}{% if loop.last %}{% if message['role'] == 'user' and add_generation_prompt %}{{ '\n### Trả lời:' }}{% endif %}{% endif %}{% endfor %}",
|
| 39 |
"clean_up_tokenization_spaces": false,
|
| 40 |
"eos_token": "</s>",
|
| 41 |
"model_max_length": 8192,
|
| 42 |
"pad_token": "<pad>",
|
| 43 |
"padding_side": "right",
|
| 44 |
"tokenizer_class": "BloomTokenizer",
|
| 45 |
-
"unk_token": "<unk>"
|
| 46 |
-
}
|
|
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"bos_token": "<s>",
|
|
|
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 8192,
|
| 7 |
"pad_token": "<pad>",
|
| 8 |
"padding_side": "right",
|
| 9 |
"tokenizer_class": "BloomTokenizer",
|
| 10 |
+
"unk_token": "<unk>",
|
| 11 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' and loop.first %}{{ '### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'user' %}{{ '\n### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'assistant' %}{{ '\n### Trả lời: ' + message['content'] + eos_token }}{% endif %}{% if loop.last %}{% if message['role'] == 'user' and add_generation_prompt %}{{ '\n### Trả lời:' }}{% endif %}{% endif %}{% endfor %}"
|
| 12 |
+
}
|