Zephyr
Hugging FaceHugging Face H4's open chat model line. The flagship zephyr-7b-beta is a DPO fine-tune of Mistral 7B trained with the open alignment-handbook recipe on the public UltraChat and UltraFeedback datasets, making the whole run reproducible. The line also includes a 141B mixture-of-experts ORPO variant.
Scored on zephyr-7b-beta. A late-2023 model, so its capability reflects that generation. Verified 2026-08-13 via the model card and the alignment-handbook repository.
Openness
5 high confidence- weights
- open(MIT
- data
- open(UltraChat_200k + UltraFeedback_binarized, both MIT, ungated)
- code
- open(alignment-handbook DPO recipe, Apache-2.0)
- license
- MIT(OSI)
Genuinely fully open: MIT weights, both DPO training datasets public and MIT-licensed, and end-to-end training code (the alignment handbook) under Apache-2.0 that reproduces zephyr-7b-beta. That is open source at the top of the scale. One caveat that does not change the class: the upstream UltraChat and UltraFeedback sets were partly generated with OpenAI model outputs, though the released Hugging Face artifacts are themselves open and MIT.
- https://huggingface.co/HuggingFaceH4/zephyr-7b-beta recorded 2026-08-13
`license:mit` in the repo tags and `"gated":false` in the embedded repo state; DPO fine-tune of Mistral-7B on the public UltraChat and UltraFeedback mixtures, both named on the card
- https://github.com/huggingface/alignment-handbook recorded 2026-08-13
Apache-2.0; contains all training code to replicate zephyr-7b-beta
Adoption
3 high confidenceThe four declared artifacts sum to 232,148 downloads in the trailing 30 days (HuggingFaceH4/zephyr-7b-beta 142,355; HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 91; HuggingFaceH4/ultrachat_200k 73,327; HuggingFaceH4/ultrafeedback_binarized 16,375), which bands at level 3 (100K-1M) on the software and model adoption scale.
- https://huggingface.co/api/models/HuggingFaceH4/zephyr-7b-beta recorded 2026-08-13
142,355 downloads in the trailing 30 days for HuggingFaceH4/zephyr-7b-beta
- https://huggingface.co/api/models/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 recorded 2026-08-13
91 downloads in the trailing 30 days for HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
- https://huggingface.co/api/datasets/HuggingFaceH4/ultrachat_200k recorded 2026-08-13
73,327 downloads in the trailing 30 days for HuggingFaceH4/ultrachat_200k
- https://huggingface.co/api/datasets/HuggingFaceH4/ultrafeedback_binarized recorded 2026-08-13
16,375 downloads in the trailing 30 days for HuggingFaceH4/ultrafeedback_binarized
Capability
2 high confidenceNotable late-2023 capability (a 7B beating much larger chat models on MT-Bench at release), but weak by 2026 standards (GSM8K 12.74, DROP 9.66 on the leaderboard). Low-tier on a scale where 5 = current frontier chat. Scored 2.
- https://huggingface.co/HuggingFaceH4/zephyr-7b-beta recorded 2026-08-13
model-index - MT-Bench score 7.34 (source lmsys/mt-bench) and AlpacaEval win rate 0.906 (source tatsu-lab/alpaca_eval); Open LLM Leaderboard avg 52.15
Verified 2026-08-13