Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +4 -24
tokenizer_config.json
CHANGED
@@ -8,34 +8,14 @@
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
-
},
|
12 |
-
"250680": {
|
13 |
-
"content": "<|im_start|>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"250681": {
|
21 |
-
"content": "<|im_end|>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
}
|
28 |
},
|
29 |
-
"
|
30 |
-
|
31 |
-
"<|im_end|>"
|
32 |
-
],
|
33 |
-
"bos_token": "<|im_start|>",
|
34 |
-
"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 %}",
|
35 |
"clean_up_tokenization_spaces": true,
|
36 |
-
"eos_token": "<|
|
37 |
"model_max_length": 1024,
|
38 |
-
"pad_token": "<|
|
39 |
"tokenizer_class": "GPT2Tokenizer",
|
40 |
"unk_token": "<|endoftext|>"
|
41 |
}
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
12 |
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{{ system_message }}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% elif (message['role'] == 'assistant') != (loop.index0 % 2 == 1) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{'\n\n' + 'Human: ' + message['content']}}{% elif message['role'] == 'assistant' %}{{'\n\n' + 'Assistant: ' + message['content']}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] == 'user' %}{{ '\n\n' + 'Assistant:' }}{% endif %}",
|
|
|
|
|
|
|
|
|
15 |
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
"tokenizer_class": "GPT2Tokenizer",
|
20 |
"unk_token": "<|endoftext|>"
|
21 |
}
|