Kristaller486's picture

Kristaller486

kristaller486

AI & ML interests

NLP, Machine Translation

Recent Activity

liked a model about 2 hours ago
Wan-AI/Wan2.1-T2V-14B
liked a model about 2 hours ago
Wan-AI/Wan2.1-T2V-1.3B
liked a model about 19 hours ago
slprl/slam
View all activity

Organizations

Social Post Explorers's profile picture

kristaller486's activity

reacted to s-emanuilov's post with 🔥 17 days ago
view post
Post
5158
Tutorial 💥 Training a non-English reasoning model with GRPO and Unsloth

I wanted to share my experiment with training reasoning models in languages other than English/Chinese.

Using Llama 3.1 8B as base, GRPO trainer from trl, and Unsloth optimizations, I got a working prototype in Bulgarian after ~5 hours on an L40S GPU. The approach should work for any language where the base model has some pre-training coverage.

Full code and tutorial here: https://unfoldai.com/reasoning-in-a-non-english-language/

The model itself: s-emanuilov/LLMBG-Llama-3.1-8B-BG-Reasoning-v0.1

I hope this helps anyone looking to build reasoning models in their language.
·