{ "_origin": "filtered from Qwen/Qwen3-1.7B-Base: dropped non-EN/ZH language tokens (23282 of 151643)", "add_prefix_space": false, "backend": "tokenizers", "bos_token": null, "clean_up_tokenization_spaces": false, "eos_token": "<|endoftext|>", "errors": "replace", "is_local": true, "local_files_only": false, "model_max_length": 131072, "pad_token": "<|endoftext|>", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null }