add tokenizer
Browse files- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<eop>", "<eod>"]}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
|
| 3 |
+
size 798011
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/46f47734f3dcaef7e236b9a3e887f27814e18836a8db7e6a49148000058a1a54.2a683f915238b4f560dab0c724066cf0a7de9a851e96b0fb3a1e7f0881552f53", "name_or_path": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}
|