xiaopel commited on
Commit
c94ef96
1 Parent(s): 299d760

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"</s>": 50257, "<pad>": 50258, "<s>": 50259, "<sep>": 50260}
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": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": "<sep>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/16a2f78023c8dc511294f0c97b5e10fde3ef9889ad6d11ffaa2a00714e73926e.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff