mrm8488 commited on
Commit
3b27214
1 Parent(s): fb7752d

Add tokenizer files

Browse files
Files changed (4) hide show
  1. merges.txt +1 -1
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +1 -1
  4. 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
- {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "mrm8488/longformer-base-4096-spanish", "do_lower_case": false, "tokenizer_file": "/root/.cache/huggingface/transformers/b5855f13c9a61de4b125a46aecb50ce5e6fce42bb015b9a9878ecfd3b208134a.77e23835743bc2dbd73aadbb18fd789f80874582c38c5ceef526bad321de9250", "tokenizer_class": "RobertaTokenizer"}
 
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