sarvam-user
commited on
Commit
•
a3112af
1
Parent(s):
be2d4b9
Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "[PAD]",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
-
"pad_token":
|
36 |
"sp_model_kwargs": {},
|
37 |
"spaces_between_special_tokens": false,
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "[PAD]",
|
36 |
"sp_model_kwargs": {},
|
37 |
"spaces_between_special_tokens": false,
|
38 |
"tokenizer_class": "LlamaTokenizer",
|