Instruction Tuned

Nous Hermes

Nous Research's steerable open-weight models, now Hermes 4 and 4.3

OpenHermes

Teknium's Mistral 7B fine-tune — 2023's go-to local chat model

Stanford Alpaca

Stanford's 2023 LLaMA fine-tune that made cheap instruction tuning standard

Zephyr

Hugging Face's 2023 DPO-tuned Mistral 7B, now a reference model