Spaces:
Sleeping
Sleeping
Commit History
-
Add LoRA checkpoint, benchmark results table, and updated README
Aditya- checkpoint-25/: LoRA fine-tune checkpoint for Qwen2.5-1.5B-Instruct (r=8, alpha=32, target q_proj+v_proj, trained on 50-topic CS Q&A data) - README: Add Benchmark Results table with real numbers from benchmark_cache.json (Baseline 81.5% acc / 1.46s, RAG 79.9% acc / 4.19s across 50 questions) - README: Updated project structure to include checkpoint-25/ and run_benchmark.py - README: Step 4 now shows how to merge LoRA adapter into finetuned_model/268a4fa