Running
on
A100
849
🪁
Zephyr 7B
Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook
Note Chat with our Zephyr 7B models!
-
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 116
HuggingFaceH4/zephyr-7b-beta
Text Generation • Updated • 285k • 1.44kNote A state-of-the-art chat model at the 7B parameter scale. Trained on synthetic data with a mix of SFT and DPO.
HuggingFaceH4/zephyr-7b-alpha
Text Generation • Updated • 84.7k • 1.07kNote The precursor to Zephyr-7B-β. Trained on synthetic data with a mix of SFT and DPO.
HuggingFaceH4/mistral-7b-sft-beta
Text Generation • Updated • 37k • 23Note The SFT model used for the DPO training of Zephyr-7B-β
HuggingFaceH4/mistral-7b-sft-alpha
Text Generation • Updated • 916 • 2Note The SFT model used for the DPO training of Zephyr-7B-α
HuggingFaceH4/ultrachat_200k
Viewer • Updated • 40.4k • 347Note The SFT dataset used to train Zephyr-7B-β
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 48.1k • 176Note The dataset of AI preferences used to train Zephyr-7B-β with DPO