Upload tokenizer
Browse files- README.md +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
README.md
CHANGED
|
@@ -6,11 +6,11 @@ base_model:
|
|
| 6 |
tags:
|
| 7 |
- transformers
|
| 8 |
pipeline_tag: text-classification
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: jacob-24b
|
| 11 |
results: []
|
| 12 |
-
language:
|
| 13 |
-
- de
|
| 14 |
---
|
| 15 |
|
| 16 |
<p align="center">
|
|
|
|
| 6 |
tags:
|
| 7 |
- transformers
|
| 8 |
pipeline_tag: text-classification
|
| 9 |
+
language:
|
| 10 |
+
- de
|
| 11 |
model-index:
|
| 12 |
- name: jacob-24b
|
| 13 |
results: []
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
<p align="center">
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|