mGPT-Peter-2E / tokenizer_config.json
pszemraj's picture
add tokenizer
345035c
raw
history blame contribute delete
614 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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "pszemraj/mGPT-Peter-mwe", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}