add fast tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>"}
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "additional_special_tokens": ["<madeupword0>", "<madeupword1>", "<madeupword2>", "<madeupword3>", "<madeupword4>", "<madeupword5>", "<madeupword6>"]}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json", "additional_special_tokens": ["<madeupword0>", "<madeupword1>", "<madeupword2>", "<madeupword3>", "<madeupword4>", "<madeupword5>", "<madeupword6>"], "tokenizer_file": null, "tokenizer_class": "XGLMTokenizer"}
|