Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +3 -43
tokenizer_config.json
CHANGED
@@ -25,46 +25,6 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<CLS>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<SEP>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<EOD>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
-
},
|
53 |
-
"32003": {
|
54 |
-
"content": "<MASK>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": false,
|
57 |
-
"rstrip": false,
|
58 |
-
"single_word": false,
|
59 |
-
"special": true
|
60 |
-
},
|
61 |
-
"32004": {
|
62 |
-
"content": "<PAD>",
|
63 |
-
"lstrip": false,
|
64 |
-
"normalized": false,
|
65 |
-
"rstrip": false,
|
66 |
-
"single_word": false,
|
67 |
-
"special": true
|
68 |
}
|
69 |
},
|
70 |
"bos_token": "<s>",
|
@@ -73,12 +33,12 @@
|
|
73 |
"eos_token": "</s>",
|
74 |
"legacy": false,
|
75 |
"mask_token": "<MASK>",
|
76 |
-
"model_max_length":
|
77 |
"pad_token": "</s>",
|
78 |
-
"padding_side": "
|
79 |
"sep_token": "<SEP>",
|
80 |
"sp_model_kwargs": {},
|
81 |
"tokenizer_class": "LlamaTokenizer",
|
82 |
"unk_token": "<unk>",
|
83 |
"use_default_system_prompt": false
|
84 |
-
}
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
"bos_token": "<s>",
|
|
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
35 |
"mask_token": "<MASK>",
|
36 |
+
"model_max_length": 4096,
|
37 |
"pad_token": "</s>",
|
38 |
+
"padding_side": "left",
|
39 |
"sep_token": "<SEP>",
|
40 |
"sp_model_kwargs": {},
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
"unk_token": "<unk>",
|
43 |
"use_default_system_prompt": false
|
44 |
+
}
|