peggyhuang commited on
Commit
0fc1cfc
1 Parent(s): 33224d5

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|sep|>": 50257}
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": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "sep_token": "<|sep|>"}
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, "name_or_path": "/tmp/gpt2_qrecc_accu64_lr5", "tokenizer_file": "/tmp/gpt2_qrecc_accu64_lr5/tokenizer.json", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff