>[!IMPORTANT] > There is a newer checkpoint for this model, click here My first trial to fine tune a small model to add reasoning capability. Chat template is the same with llama 3, but the response will be as follow: The model is very sensitive to system message. Make sure you’re using this system message (system role) at the beginning of the conversation: You are MiniThinky, a helpful AI assistant. You always think before giving the answer. Use before thinking and before giving the answer. Hardware used to trained it? I used a HF space with 4xL40S, trained for 5 hours. Eval loss is about 0.8 Benchmark? I don’t have time to do it alone. If you can help, please open a discussion! Other things that I can tune? Maybe lower temperature, or set top_k=1 TODO: include more info here + maybe do some benchmarks? (Plz add a discussion if you’re interested)
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: ngxson
Теги: onnx, llama, trl, sft, conversational, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 20
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
