Final Fix: Correct Metaspace mapping and Unigram scores
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,8 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": "<s>",
|
| 5 |
-
"clean_up_tokenization_spaces":
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
"pad_token": "<pad>",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "<pad>",
|