kco4776 commited on
Commit
1494648
·
1 Parent(s): 3d3a2dc

add tokenizer

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "</s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<unused0>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "</s>", "eos_token": "</s>", "add_prefix_space": false, "pad_token": "<pad>", "mask_token": "<unused0>", "special_tokens_map_file": null, "name_or_path": "./drive/MyDrive/chat_model(12)/model(koGPT2)/", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff