Upgrade to 50k Vocab - Support Al-Qur'an & Indo (No More Broken Bytes)
Browse files- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -8
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,13 +1,12 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
-
"bos_token": "
|
| 4 |
-
"eos_token": "
|
| 5 |
-
"
|
| 6 |
-
|
| 7 |
-
"### AWA:"
|
| 8 |
-
],
|
| 9 |
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
"pad_token": "[PAD]",
|
| 11 |
-
"tokenizer_class": "
|
| 12 |
-
"unk_token": "
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[BOS]",
|
| 5 |
+
"eos_token": "[EOS]",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": true,
|
|
|
|
|
|
|
| 8 |
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
| 12 |
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|