Hugging Face: Zephyr 7B

Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO).

Zephyr 7B tiene una ventana de contexto de 4096 tókenes.

Zephyr 7B se lanzó el 2 de agosto de 2023. Su fecha límite de conocimientos es 31 de octubre de 2023.