Pinned Loading

1. llm-data-distillation-suite llm-data-distillation-suite Public

   A data distillation pipeline that automates the generation, evaluation, and filtering of SFT (Supervised Fine-Tuning) training data using multiple LLMs.

   Python

2. RLVR-Alignment RLVR-Alignment Public

   RLVR-Alignment is a RLVR / GRPO alignment experiment repository for large language models, primarily used for research and reproduction of reinforcement learning alignment workflows based on Verifi…

   Python

3. vlm-ocr-parser vlm-ocr-parser Public

   vlm-ocr-parser is a lightweight wrapper built on top of PaddleOCR-VL, designed to parse images / PDFs / directories into structured outputs that are easy to plug into RAG / retrieval / diff & QC pi…

   Python

4. competitors_searcher competitors_searcher Public

   A minimal, production-ready micro-service that turns raw competitor data into a live semantic search API on top of DashVector.

   Python