29 skills found
JudgmentLabs / JudgevalThe open source post-building layer for agents. Our environment data and evals power agent post-training (RL, SFT) and monitoring.
InternScience / GraphGenGraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
chaoswork / Sft Datasets开源SFT数据集整理,随时补充
Gen-Verse / ReasonFlux[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.
argilla-io / NotusNotus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach
synlp / ChiMed GPTChiMed-GPT is a Chinese medical large language model (LLM) built by continually training Ziya-v2 on Chinese medical data, where pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF) are comprehensively performed on it.
ServiceNow / SyGraSyGra - Graph-oriented Synthetic data generation Pipeline
yiyepiaoling0715 / Codellm Data Preprocess Pipeline代码大模型 预训练&微调&DPO 数据处理 业界处理pipeline sota
ZJU-REAL / TimeHC RLThis repository is the official implementation of TimeHC-RL (Distilabel (Data Generation) + TRL (SFT) + VeRL (GRPO)).
ly-geming / AnyCam2RosTurn any camera (Insta360, RealSense, USB webcam, etc.) into ROS2 image topics. Unified config for VLA deployment and SFT data collection.
vvincenttttt / Awesome 3D AutoLabeling ToolsPapers, code and datasets about deep learning/LLM SFT data auto-labeling.
xiatingyu / SFT DataSelection At ScaleNo description available
quanshr / AugCon[AAAI 2025]Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity
requestsession / IndexGPTIndexGPT: 本地 AI 科研助手（RAG + SFT + LoRA）| Local AI research assistant for PDF parsing, retrieval QA, SFT data generation, and LoRA training.
Pe46dro / Bash MySQL Database SFTP FTP BackupA small script to upload backup of MySQL database to an external FTP server
ChristopheZhao / SFT Data GenerationInstruction Tuning data generation uses LLM in a specific scenario.
seanzhang-zhichen / Qwen WisdomVastQwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and 2,000 single-turn self-cognition data, using the training methods of DORA and LORA+ based on Qwen1.5-7B as the base. Compared to Qwen1.5-7B-Chat, it has improved mathematical abilities by 5.16%, 12.8% on the Human
NVIDIA / NvflowWorkflow orchestration framework for end-to-end synthetic data generation (SDG), training (SFT), and evaluation pipelines built on NVIDIA's NeMo ecosystem
Zizhao-HUANG / Financial Llm Dataset PipelineModular pipeline for collecting, processing, and exporting financial data into LLM-ready formats (CPT/SFT/TXT). Built on a raw→silver→gold architecture with built-in auditing.
EthioNLP / Afri Sft DataThis repository generates instruction tuning dataset from different datasets.
