plotly_gpt_neo_1_3B / tokenizer_config.json
lagodw's picture
full sample tokenizer
b6c0a87
raw
history blame
651 Bytes
{"unk_token": {"content": "<UNK>", "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": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "pad_token": "<PAD>", "sep_token": "<SEP>", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}