FIX: Complete compilation of 32k vocabulary into tokenizer.json
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +10 -2
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,10 +1,18 @@
|
|
| 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>",
|
| 8 |
-
"tokenizer_class": "
|
| 9 |
-
"unk_token": "<unk>"
|
|
|
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<s>",
|
| 9 |
+
"</s>",
|
| 10 |
+
"<pad>"
|
| 11 |
+
],
|
| 12 |
+
"is_local": true,
|
| 13 |
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
"pad_token": "<pad>",
|
| 15 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 16 |
+
"unk_token": "<unk>",
|
| 17 |
+
"use_default_system_prompt": false
|
| 18 |
}
|