Git Stars Git Stars

#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
Total Repositories
73,413
Total Stars
4,318
Avg Stars/Repo
1
modelscope/ms-swift

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).

modelscope
โญ 16,138 Python ๐Ÿ‘ค modelscope Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-08-01
2
adongwanai/AgentGuide

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

adongwanai
โญ 12,147 MDX ๐Ÿ‘ค adongwanai User ๐Ÿ• Updated 2026-11-05 ๐Ÿ“… Created 2025-11-03
3
MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

MakazhanAlpamys
โญ 10,703 Python ๐Ÿ‘ค MakazhanAlpamys User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-20
4
oumi-ai/oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

oumi-ai
โญ 9,441 Python ๐Ÿ‘ค oumi-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-05-07
5
meta-pytorch/torchtune

PyTorch native post-training library

meta-pytorch
โญ 5,820 Python ๐Ÿ‘ค meta-pytorch Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2023-10-20
6
walkinglabs/hands-on-modern-rl

๐Ÿš€ An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

walkinglabs
โญ 4,936 Jupyter Notebook ๐Ÿ‘ค walkinglabs Organization ๐Ÿ• Updated 2026-10-23 ๐Ÿ“… Created 2026-04-10
7
datawhalechina/diy-llm

Covers pre-training data, Tokenizers, Transformers, MoE, distributed training, scaling laws, inference, and alignment. 6 progressive coding assignments for full-stack LLM learning.

datawhalechina
โญ 3,035 Jupyter Notebook ๐Ÿ‘ค datawhalechina Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-11-24
8
AI-Hypercomputer/maxtext

A simple, performant, and scalable Jax LLM!

AI-Hypercomputer
โญ 2,468 Python ๐Ÿ‘ค AI-Hypercomputer Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-02-28
9
ssbuild/chatglm_finetuning

chatglm 6b finetuning and alpaca finetuning

ssbuild
โญ 1,531 Python ๐Ÿ‘ค ssbuild User ๐Ÿ• Updated 2025-03-09 ๐Ÿ“… Created 2023-03-14
10
Alibaba-NLP/ZeroSearch

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Alibaba-NLP
โญ 1,305 Python ๐Ÿ‘ค Alibaba-NLP Organization ๐Ÿ• Updated 2025-08-16 ๐Ÿ“… Created 2025-05-07
11
InternScience/GraphGen

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

InternScience
โญ 1,236 Python ๐Ÿ‘ค InternScience Organization ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2025-01-08
12
AgileRL/AgileRL

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.

AgileRL
โญ 971 Python ๐Ÿ‘ค AgileRL Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-03-01
13
invergent-ai/surogate

Train and serve LLMs at extreme speed and massive throughput.

invergent-ai
โญ 888 C++ ๐Ÿ‘ค invergent-ai Organization ๐Ÿ• Updated 2026-11-05 ๐Ÿ“… Created 2026-01-02
14
baidu-baige/LoongForge

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.

baidu-baige
โญ 881 Python ๐Ÿ‘ค baidu-baige Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-04-23
15
ScienceOne-AI/DeepSeek-671B-SFT-Guide

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.

ScienceOne-AI
โญ 806 Python ๐Ÿ‘ค ScienceOne-AI User ๐Ÿ• Updated 2025-03-13 ๐Ÿ“… Created 2025-03-07
16
choosewhatulike/trainable-agents

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

choosewhatulike
โญ 603 Python ๐Ÿ‘ค choosewhatulike User ๐Ÿ• Updated 2024-10-29 ๐Ÿ“… Created 2023-10-08
17
ukairia777/tensorflow-nlp-tutorial

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.

ukairia777
โญ 580 Jupyter Notebook ๐Ÿ‘ค ukairia777 User ๐Ÿ• Updated 2026-06-05 ๐Ÿ“… Created 2021-12-30

Frequently Asked Questions

1

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).

2

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++.

3

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.