fine-tuning repositories

Trending repositories tagged fine-tuning, ranked by trending score. Updated daily.

  1. 1
    datamllab/OpenEBFM

    Open-source code for training and scaling up energy-based foundation models.

    GitHub · Python · 404 stars · 29 forks · +274 stars in 24 hours · Trending score 4.25

  2. 2
    unslothai/unsloth

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

    GitHub · Python · 79,929 stars · 7,440 forks · +116 stars in 24 hours · Trending score 3.96

  3. 3
    orionsheep/wordlink

    AI-powered vocabulary learning — a fine-tuned 1.5B model (SFT+DPO) that runs offline in your browser. Live: wordlink.lifeplayertribe.com

    GitHub · TypeScript · 439 stars · 55 forks · +197 stars in 24 hours · Trending score 3.91

  4. 4
    MakazhanAlpamys/Soup

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

    GitHub · Python · 10,714 stars · 1,779 forks · +56 stars in 24 hours · Trending score 3.47

  5. 5
    NVIDIA-NeMo/Nemotron

    Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

    GitHub · Jupyter Notebook · 2,375 stars · 496 forks · +82 stars in 24 hours · Trending score 3.42

  6. 6
    hiyouga/LlamaFactory

    Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

    GitHub · Python · 76,178 stars · 9,384 forks · +33 stars in 24 hours · Trending score 3.08

  7. 7
    amitshekhariitbhu/ai-engineering-interview-questions

    Your Cheat Sheet for AI Engineering Interview – Questions and Answers.

    GitHub · Markdown · 3,716 stars · 667 forks · +36 stars in 24 hours · Trending score 2.98

  8. 8
    bentoml/OpenLLM

    Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

    GitHub · Python · 12,610 stars · 852 forks · +49 stars in 24 hours · Trending score 2.61

  9. 9
    AIDotNet/OpenDeepWiki

    OpenDeepWiki is the open-source version of the DeepWiki project, aiming to provide a powerful knowledge management and collaboration platform. The project is mainly developed using C# and TypeScript, supporting modular design, and is easy to expand and customize.

    GitHub · C# · 3,673 stars · 467 forks · +36 stars in 24 hours · Trending score 2.54

  10. 10
    run-llama/llama_index

    LlamaIndex is the document processing platform for AI

    GitHub · Python · 52,973 stars · 8,611 forks · +8 stars in 24 hours · Trending score 2.51

  11. 11
    shootthesound/Fizgig

    Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models

    GitHub · Python · 794 stars · 84 forks · +9 stars in 24 hours · Trending score 2.24

  12. 12
    datawhalechina/base-llm

    从 NLP 到 LLM 的算法全栈教程,在线阅读地址:https://datawhalechina.github.io/base-llm/

    GitHub · Jupyter Notebook · 1,150 stars · 125 forks · +21 stars in 24 hours · Trending score 2.11

  13. 13
    calmrocks/ai-engineer-notebooks

    Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.

    GitHub · Jupyter Notebook · 756 stars · 76 forks · +15 stars in 24 hours · Trending score 2.05

  14. 14
    modelscope/ms-cookbook

    魔搭紫皮书|ModelScope Cookbook:面向开发者的开源模型应用实战指南,覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC,从跑通第一个模型到构建实际应用。

    GitHub · HTML · 529 stars · 88 forks · +15 stars in 24 hours · Trending score 2.00

  15. 15
    bghira/SimpleTuner

    A general fine-tuning kit geared toward image/video/audio diffusion models.

    GitHub · Python · 2,961 stars · 296 forks · +11 stars in 24 hours · Trending score 1.81

  16. 16
    huggingface/peft

    🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

    GitHub · Python · 21,913 stars · 2,680 forks · +3 stars in 24 hours · Trending score 1.79

  17. 17
    oumi-ai/oumi

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

    GitHub · Python · 9,442 stars · 801 forks · +6 stars in 24 hours · Trending score 1.68

  18. 18
    overmind-core/overmind

    The platform for continuously improving AI agents.

    GitHub · Python · 774 stars · 75 forks · +8 stars in 24 hours · Trending score 1.61

  19. 19
    ludwig-ai/ludwig

    Low-code framework for building custom LLMs, neural networks, and other AI models

    GitHub · Python · 11,793 stars · 1,212 forks · +9 stars in 24 hours · Trending score 1.58

  20. 20
    Tavris1/AI-Toolkit-Easy-Install

    One-click Portable Windows installation of 'AI-Toolkit by Ostris'

    GitHub · Batchfile · 545 stars · 41 forks · +10 stars in 24 hours · Trending score 1.56

  21. 21
    Valen-Team/Roller

    Turn agent runs into training data. Roller rolls out Claude Code, Codex, OpenClaw and four other Harnesses in disposable Docker containers, grades benchmark tasks in place, and exports SFT-ready trajectories that keep reasoning, images and compacted-context segments.

    GitHub · Python · 120 stars · 0 forks · +17 stars in 24 hours · Trending score 1.41

  22. 22
    whitecircle/halo

    Halo is an open-source framework built by White Circle for training large language and multimodal models

    GitHub · Python · 868 stars · 50 forks · +3 stars in 24 hours · Trending score 1.38

  23. 23
    Zyora-Dev/zse

    The inference engine the open-source world built for itself.

    GitHub · Python · 242 stars · 17 forks · +6 stars in 24 hours · Trending score 1.36

  24. 24
    AkashPriyadarshii/jev-curate

    High-throughput synthetic and pretraining dataset sifter for TypeSafe Jev. Rust streaming core, Parquet and JSONL I/O, typed Choice/Score/Noul judgments, speculative fan-out, 24.0 rows/sec measured.

    GitHub · Rust · 115 stars · 15 forks · +5 stars in 24 hours · Trending score 1.29