This is the merged model for LoRA https://huggingface.co/Yhyu13/phi-2-sft-alpacagpt4en-ep1-lora Quote from this discussion https://huggingface.co/microsoft/phi-2/discussions/38 Since phi2 requires remote code which HF open llm leaderboard would not accept at this moment, Here is result evaluated by chatpgpt https://github.com/tatsu-lab/alpaca_eval/pull/183 It could be a milestone for small models, we finally have one open model can run for everyone which surpass GPT3.5!
Модальности:
Генерация текста
Задача: Генерация текста
Автор: Yhyu13
Теги: phi-msft, custom_code, endpoints_compatible
Лайков: 3 | Загрузок: 44
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.