| { | |
| "add_bos_token": false, | |
| "add_prefix_space": false, | |
| "bos_token": { | |
| "__type": "AddedToken", | |
| "content": "<|startoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "do_lower_case": false, | |
| "eos_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "errors": "replace", | |
| "full_tokenizer_file": null, | |
| "max_len": 1024, | |
| "name_or_path": "./hebrew-gpt_neo-small", | |
| "pad_token": null, | |
| "special_tokens_map_file": "special_tokens_map.json", | |
| "tokenizer_class": "GPT2Tokenizer", | |
| "unk_token": { | |
| "__type": "AddedToken", | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |