Join the Fireworks Startups Program and unlock credits, expert support, and community to scale fast. Join here

Hugging Face Logo Mark

Zephyr 7B Beta

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 on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO).

Try Model

Fireworks Features

Fine-tuning

Zephyr 7B Beta can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model

Learn More

On-demand Deployment

On-demand deployments give you dedicated GPUs for Zephyr 7B Beta using Fireworks' reliable, high-performance system with no rate limits.

Learn More

Info & Pricing

Provider

Hugging Face

Model Type

LLM

Context Length

32768

Fine-Tuning

Available

Pricing Per 1M Tokens

$0.2