{ "add_prefix_space": false, "added_tokens_decoder": { "0": { "content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "<|im_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "5": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "6": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "7": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "8": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "9": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "10": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "11": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "12": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "13": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "14": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "15": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "16": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [ "<|endoftext|>", "<|im_start|>", "<|im_end|>", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ], "bos_token": "<|endoftext|>", "chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% elif message['role'] == 'assistant' %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% elif message['from'] == 'gpt' %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['from'] + '<|end_header_id|>\n\n' + message['value'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}{% endif %}", "clean_up_tokenization_spaces": false, "eos_token": "<|endoftext|>", "model_max_length": 2048, "pad_token": "", "padding_side": "left", "tokenizer_class": "GPT2Tokenizer", "unk_token": "<|endoftext|>", "vocab_size": 49152 }