Ttimofeyka
commited on
Commit
•
519a1a1
1
Parent(s):
d9741e2
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +4 -34
tokenizer_config.json
CHANGED
@@ -25,48 +25,18 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|end_of_turn|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|pad_0|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<sep>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
}
|
53 |
},
|
54 |
-
"additional_special_tokens": [
|
55 |
-
"<|end_of_turn|>",
|
56 |
-
"<|pad_0|>"
|
57 |
-
],
|
58 |
"bos_token": "<s>",
|
59 |
"clean_up_tokenization_spaces": false,
|
60 |
-
"eos_token": "
|
61 |
"legacy": true,
|
62 |
"model_max_length": 1000000000000000019884624838656,
|
63 |
-
"pad_token":
|
64 |
-
"sep_token": "<sep>",
|
65 |
"sp_model_kwargs": {},
|
66 |
"spaces_between_special_tokens": false,
|
67 |
"tokenizer_class": "LlamaTokenizer",
|
68 |
-
"trust_remote_code": false,
|
69 |
"unk_token": "<unk>",
|
70 |
-
"use_default_system_prompt": true
|
71 |
-
"use_fast": true
|
72 |
}
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
31 |
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": null,
|
|
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": true
|
|
|
42 |
}
|