OpenHermes 2.5
Fine-tuned Mistral 7B achieving top performance through curated training data.
About
OpenHermes 2.5 by Nous Research is a fine-tune of Mistral 7B trained on a large corpus of curated, mostly synthetic instruction data, continuing the OpenHermes 2 line with additional code datasets. Adding a share of code instruction data improved several non-code benchmarks as well, and the model is a popular base for further fine-tuning. Released under the Apache 2.0 license with weights on Hugging Face.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Apache-2.0
- Minimum VRAM
- 6 GB
- Added
- Apr 3, 2026
Related Tools
Open-weight models by Google in 2B, 9B, and 27B sizes with strong performance.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.
Open-weight LLM family by Alibaba with strong multilingual and coding abilities.
Small language model by Microsoft in 3.8B size with strong benchmark performance.
Open-access 176B parameter multilingual LLM by BigScience supporting 46 languages.
Retrieval-augmented generation optimized LLM by Cohere with 128K context.