Pinned Loading
-
grpo-from-scratch
grpo-from-scratch PublicFrom-scratch GRPO (DeepSeek-R1) implementation reaching 74.2% on MATH, with full ablation sweep
Python
-
filing-sense
filing-sense PublicRAG pipeline for SEC 10-K filing analysis — FinQA dataset, hybrid retrieval (BM25 + FAISS + reranker), LoRA & Full SFT fine-tuning on Qwen2.5-3B
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.

