Add tokenizer files
Browse files- merges.txt +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
d e
|
3 |
Ġ e
|
4 |
Ġ de
|
|
|
1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
2 |
d e
|
3 |
Ġ e
|
4 |
Ġ de
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "mrm8488/longformer-base-4096-spanish", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|