gpt2-small-spanish / tokenizer_config.json

First version of the gpt2-small-spanish model and tokenizer. Primera version del modelo y tokenizer gpt2-small-spanish.

9e8d339 almost 4 years ago

620 Bytes

{"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": "/home/jobregon/.fastai/data/eswiki/ByteLevelBPE_tokenizer_es", "errors": "replace"}