It seems mistral finally released their own version of a small 3.1 2503 with CoT reasoning pattern embedding. Before this the best CoT finetune of Small was DeepHermes with deepseeks r1 distill patterns. According to the technical report, mistral baked their own reasoning patterns for this one so its not just another deepseek distill finetune.

HuggingFace

Blog

Magistral technical research academic paper

you are viewing a single comment's thread
view the rest of the comments
[–] 6 points 1 year ago

good work Mistral :)

  • source