Nous Research
3 models in Artifacts Logshuggingface.co/NousResearch
DeepHermes-3-Mistral-24B-Preview02 Mar 2025
24BApache-2.0399 · 30d
A R1-based fine-tune onto Mistral 3 24B. Similar to the Llama-based version, the model can switch between outputting reasoning tokens based on the system prompt.
Hermes-3-Llama-3.1-405B13 Aug 2024
643 · 30d
One of the strongest open fine-tunes out there. Really, it's most exciting to see fine-tunes of Llama 405B starting to happen! More here.
Hermes-2-Theta-Llama-3-70B14 Jun 2024
2.4K · 30d
A general chat model from one of the normal fine-tuning groups!