gitaskhub

Sovereign fine-tuning demo to remove bias out of open weight Chinese models. Compare stock Qwen2.5-7B with a UK (Western)-aligned LoRA fine-tune, side by side.

Stars · 3
Language · Python
License · MIT
Ask anything about this repo to start.
Full explanation on explaingit →

By chatting or signing in you agree to the Terms and chat-message logging (revocable in History).