| { | |
| "tokenizer_class": "CortexTokenizer", | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_cortex.CortexTokenizer", | |
| null | |
| ] | |
| }, | |
| "model_max_length": 512, | |
| "bos_token": "<|endoftext|>", | |
| "eos_token": "<|endoftext|>", | |
| "pad_token": "<|pad|>", | |
| "unk_token": "<|unk|>", | |
| "additional_special_tokens": [ | |
| "<|system|>", | |
| "<|user|>", | |
| "<|assistant|>", | |
| "<|end|>", | |
| "<|doc|>", | |
| "<|code|>" | |
| ], | |
| "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|system|>\n{{ message['content'] }}\n<|end|>\n{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}\n<|end|>\n{% else %}<|assistant|>\n{{ message['content'] }}\n<|end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}", | |
| "tokenizer_files": [ | |
| "vocab.json", | |
| "merges.txt" | |
| ] | |
| } |