Switch from local SmolLM2 model to Qwen2.5-72B-Instruct via HuggingFace Inference API e55b892 Maximofn commited on Mar 2
Refactor app.py with improved model initialization and endpoint structure e4413df Maximofn commited on Mar 2
Re-enable HuggingFace model integration and restore generate endpoint e2f16cb Maximofn commited on Mar 2
Temporarily disable HuggingFace model integration and simplify FastAPI endpoints b0424cf Maximofn commited on Mar 2
Switch HuggingFace model from Qwen to SmolLM for lightweight inference a824dd2 Maximofn commited on Mar 2
Refactor HuggingFace model integration and simplify token handling 159fcfe Maximofn commited on Mar 2
Add token logging and debug information for HuggingFace authentication 20d2599 Maximofn commited on Mar 2
Update project documentation and dependencies to English, modify HuggingFace model initialization 5f2f118 Maximofn commited on Mar 2
