Deploy native SentencePiece-backed 16K Unigram tokenizer with verified space preservation.
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"eos_token": "</s>",
|