Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +47 -0
tokenizer_config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|im_start|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<|im_start|>",
|
32 |
+
"<|im_end|>",
|
33 |
+
"<|endoftext|>"
|
34 |
+
],
|
35 |
+
"bos_token": "<|im_start|>",
|
36 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\\nYou are a specialized DevOps assistant. You help with DevOps tasks only.<|im_end|>\\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "<|im_end|>",
|
39 |
+
"errors": "replace",
|
40 |
+
"model_max_length": 32768,
|
41 |
+
"pad_token": "<|endoftext|>",
|
42 |
+
"sp_model_kwargs": {},
|
43 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
44 |
+
"unk_token": "<|endoftext|>",
|
45 |
+
"use_fast": true,
|
46 |
+
"vocab_size": 151646
|
47 |
+
}
|