#sft Repositories
Discover 17 active open source GitHub repositories tagged with #sft, accumulating 73,413 total stars (averaging 4,318 stars per project). Leading this topic is modelscope/ms-swift with 16,138 stars.
17 repositories total
Use PEFT or full-parameter training for CPT/SFT/DPO/GRPO on 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, LLaVA, Phi4, ...) (AAAI 2025).
AI Agent Development Guide | Agent Harness | Context Engineering | Advanced RAG | MCP | Agentic RL (Reinforcement Learning) | Hands-on LangGraph | 12,000+ LLM Interview Questions | Job Hunting for Algorithm / Development Roles | Switching Careers to LLMs
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
๐ An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
Covers pre-training data, Tokenizers, Transformers, MoE, distributed training, scaling laws, inference, and alignment. 6 progressive coding assignments for full-stack LLM learning.
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3, and more.
An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions.
Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"
A Deep Learning NLP repository that summarizes text preprocessing, Topic Models, and downstream tasks of state-of-the-art models such as BERT, GPT, and LLMs using TensorFlow.
Frequently Asked Questions
What is the most popular #sft repository on GitHub?
The top ranked open source #sft project on GitHub is modelscope/ms-swift with 16,138 stars. Use PEFT or full-parameter training for CPT/SFT/DPO/GRPO on 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, LLaVA, Phi4, ...) (AAAI 2025).
Which programming languages are most used in #sft repositories?
Among the top ranked #sft projects on GitHub, the most common programming languages are Python, Jupyter Notebook, MDX, C++.
How is the #sft repository ranking calculated?
We track 17 active open source repositories tagged with #sft (500+ stars), totaling 73,413 stars with an average of 4,318 stars per repository. Rankings update daily from the GitHub API.