Phase 2 Quick Fix: Switch to clean Qwen2.5-0.5B-Instruct base model e89521f Running verified anktechsol commited on Nov 8
Phase 1 Quick Wins: Optimize inference for 3-5x speed boost 9c878f1 verified anktechsol commited on Nov 8
Remove OAuth config and update README for direct model loading 76dd32e verified anktechsol commited on Oct 3
Fix app.py: Replace InferenceClient with direct model loading using transformers d5f4c16 verified anktechsol commited on Oct 3
Duplicate from gradio-templates/chatbot 8f136d4 verified anktechsol pngwn HF Staff commited on Sep 24