gpt2-small-czech-cs / tokenizer_config.json
spital's picture
Upload tokenizer_config.json
34f878d
{"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, "pad_token": "<|endoftext|>", "special_tokens_map_file": null, "name_or_path": "/shared/data/ptwiki/ByteLevelBPE_tokenizer_pt", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}