add tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +8 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"mask_token": "<mask>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"sep_token": "</s>",
|
| 7 |
+
"unk_token": "<unk>"
|
| 8 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"do_lowercase_and_remove_accent": false,
|
| 6 |
+
"id2lang": null,
|
| 7 |
+
"lang2id": null,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"name_or_path": "allegro/herbert-base-cased",
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"special_tokens_map_file": "/home/bartekk/.cache/huggingface/transformers/a77c29d6c21e653166565b0d51ea0a46b918191512e0ae894422060267a0f436.b8e113717eb1828d09e47de853cf49c8fad05ebdce24df2614cd942dc23e2a77",
|
| 14 |
+
"tokenizer_class": "HerbertTokenizer",
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|