danielhanchen
commited on
Commit
•
bcfbc1d
1
Parent(s):
aeb5075
Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -32,9 +32,9 @@
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
-
"model_max_length":
|
36 |
"pad_token": "<unk>",
|
37 |
-
"padding_side": "
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
"pad_token": "<unk>",
|
37 |
+
"padding_side": "left",
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|