Commit
•
180f75e
1
Parent(s):
044a85f
add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<START>", "eos_token": "<END>", "unk_token": "<UNK>"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<START>", "eos_token": "<END>", "unk_token": "<UNK>", "special_tokens_map_file": "/home/dracoglacius/StemmlerProject/MIke_GPT2/WordBBPEModels/8_24_Word_Lvl_GPT2/8_24_fast_word_lvl_tokenizer_noestart/special_tokens_map.json", "name_or_path": "/home/dracoglacius/StemmlerProject/MIke_GPT2/WordBBPEModels/8_24_Word_Lvl_GPT2/8_24_fast_word_lvl_tokenizer_noestart", "tokenizer_class": "PreTrainedTokenizerFast"}
|