patrickvonplaten commited on
Commit
bd59792
1 Parent(s): 108f5bc

Update tokenizer_config.json

Browse files

This is important to prevent a nasty bug at the moment. Without this fix one could load the wrong tokenizer (fast gpt2) when doing tokenizer = AutoTokenizer.from_pretrained('your/model/id'). Currently fast gpt2 doesn't work correctly with OPT and one should only use the slow one see: https://huggingface.co/facebook/opt-6.7b#how-to-use

Files changed (1) hide show
  1. tokenizer_config.json +1 -1
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "facebook/opt-350m", "model_max_length": 1024, "tokenizer_class": "GPT2Tokenizer"}
1
+ {"unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "facebook/opt-350m", "model_max_length": 1024}