This model is trained by fine-tuning llama-2 with recycled WizardLM(70k) data V2. — Developed by: UMD Tianyi Zhou Lab — Model type: An auto-regressive language model based on the transformer architecture — License: Llama 2 Community License Agreement — Finetuned from model: meta-llama/Llama-2-7b — GitHub: Reflection-Tuning — Paper: Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning — Data: Coming soon The primary use of this model is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. The following table provides a comparison between our recycled models (V2) and baseline models on the AlpacaEval Leaderboard and Huggingface Open LLM Leaderboard. The V2 Recycled Alpaca Data and WizardLM data, and the corresponding paper will be released soon. Please consider citing our paper if you think our codes, data, or models are useful. Thank you!
Модальности:
Генерация текста
Задача: Генерация текста
Автор: umd-zhou-lab
Теги: llama, en, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 63
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.