#Fine-tuning

Showing 60 of 152 repositories tagged #fine-tuning, ranked by stars

hiyouga
hiyouga
LlamaFactory

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

Score
100
โ˜… 73.1k โ‘‚ 8.9k +120/day
Python
unslothai
unslothai
unsloth

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Score
94
โ˜… 68.0k โ‘‚ 6.1k +15/day
Python
run-llama
run-llama
llama_index

LlamaIndex is the leading document agent and OCR platform

Score
89
โ˜… 50.7k โ‘‚ 7.7k +82/day
Python
FunAudioLLM
FunAudioLLM
CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Score
78
โ˜… 22.0k โ‘‚ 2.5k +61/day
Python
huggingface
huggingface
peft

๐Ÿค— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Score
83
โ˜… 21.4k โ‘‚ 2.4k +5/day
Python
ConardLi
ConardLi
easy-dataset

A powerful tool for creating datasets for LLM fine-tuning ใ€RAG and Eval

Score
100
โ˜… 14.6k โ‘‚ 1.5k +35/day
JavaScript
bentoml
bentoml
OpenLLM

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

Score
61
โ˜… 12.4k โ‘‚ 822 +6/day
Python
axolotl-ai-cloud
axolotl-ai-cloud
axolotl

Go ahead and axolotl questions

Score
72
โ˜… 12.2k โ‘‚ 1.4k +9/day
Python
ludwig-ai
ludwig-ai
ludwig

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

Score
67
โ˜… 11.7k โ‘‚ 1.2k โ€”
Python
oumi-ai
oumi-ai
oumi

Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!

Score
56
โ˜… 9.3k โ‘‚ 783 +3/day
Python
flyteorg
flyteorg
flyte

Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.

Score
100
โ˜… 7.1k โ‘‚ 845 โ€”
Go
h2oai
h2oai
h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Score
99
โ˜… 5.0k โ‘‚ 533 +18/day
Python
Kiln-AI
Kiln-AI
Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Score
50
โ˜… 5.0k โ‘‚ 377 +2/day
Python
vllm-project
vllm-project
semantic-router

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

Score
67
โ˜… 4.9k โ‘‚ 742 +16/day
Go
LLMBook-zh
LLMBook-zh
LLMBook-zh.github.io

ใ€Šๅคง่ฏญ่จ€ๆจกๅž‹ใ€‹ไฝœ่€…๏ผš่ตต้‘ซ๏ผŒๆŽๅ†›ๆฏ…๏ผŒๅ‘จๆ˜†๏ผŒๅ”ๅคฉไธ€๏ผŒๆ–‡็ปง่ฃ

Score
84
โ˜… 4.5k โ‘‚ 340 +7/day
Python
truefoundry
truefoundry
cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

Score
44
โ˜… 4.4k โ‘‚ 390 +1/day
Python
nucleuscloud
nucleuscloud
neosync

Open Source Data Security Platform for Developers to Monitor and Detect PII, Anonymize Production Data and Sync it across environments.

Score
33
โ˜… 4.1k โ‘‚ 234 โ€”
Go
predibase
predibase
lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Score
97
โ˜… 3.8k โ‘‚ 323 +2/day
Python
hiyouga
hiyouga
ChatGLM-Efficient-Tuning

Fine-tuning ChatGLM-6B with PEFT | ๅŸบไบŽ PEFT ็š„้ซ˜ๆ•ˆ ChatGLM ๅพฎ่ฐƒ

Score
76
โ˜… 3.7k โ‘‚ 462 +1/day
Python
ZhaoJ9014
ZhaoJ9014
face.evoLVe

๐Ÿ”ฅ๐Ÿ”ฅHigh-Performance Face Recognition Library on PaddlePaddle & PyTorch๐Ÿ”ฅ๐Ÿ”ฅ

Score
74
โ˜… 3.6k โ‘‚ 760 โ€”
Python
smallcloudai
smallcloudai
refact

AI Agent that handles engineering tasks end-to-end: integrates with developersโ€™ tools, plans, executes, and iterates until it achieves a successful result.

Score
100
โ˜… 3.5k โ‘‚ 319 โ€”
Rust
aiming-lab
aiming-lab
MetaClaw

๐Ÿฆž Just talk to your agent โ€” it learns and EVOLVES ๐Ÿงฌ.

Score
96
โ˜… 3.5k โ‘‚ 445 +7/day
Python
iusztinpaul
iusztinpaul
hands-on-llms

๐Ÿฆ– ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป about ๐—Ÿ๐—Ÿ๐— ๐˜€, ๐—Ÿ๐—Ÿ๐— ๐—ข๐—ฝ๐˜€, and ๐˜ƒ๐—ฒ๐—ฐ๐˜๐—ผ๐—ฟ ๐——๐—•๐˜€ for free by designing, training, and deploying a real-time financial advisor LLM system ~ ๐˜ด๐˜ฐ๐˜ถ๐˜ณ๐˜ค๐˜ฆ ๐˜ค๐˜ฐ๐˜ฅ๐˜ฆ + ๐˜ท๐˜ช๐˜ฅ๐˜ฆ๐˜ฐ & ๐˜ณ๐˜ฆ๐˜ข๐˜ฅ๐˜ช๐˜ฏ๐˜จ ๐˜ฎ๐˜ข๐˜ต๐˜ฆ๐˜ณ๐˜ช๐˜ข๐˜ญ๐˜ด

Score
57
โ˜… 3.4k โ‘‚ 551 โ€”
Jupyter Notebook
AIDotNet
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.

Score
98
โ˜… 3.4k โ‘‚ 434 +19/day
C#
ashishpatel26
ashishpatel26
LLM-Finetuning

LLM Finetuning with peft

Score
75
โ˜… 3.0k โ‘‚ 769 +6/day
Jupyter Notebook
decodingai-magazine
decodingai-magazine
second-brain-ai-assistant-course

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

Score
100
โ˜… 2.9k โ‘‚ 509 +16/day
Jupyter Notebook
bghira
bghira
SimpleTuner

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

Score
100
โ˜… 2.9k โ‘‚ 285 โ€”
Python
stochasticai
stochasticai
xTuring

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

Score
91
โ˜… 2.7k โ‘‚ 210 +3/day
Python
pykeio
pykeio
ort

Fast ML inference & training for ONNX models in Rust

Score
0
โ˜… 2.4k โ‘‚ 254 +3/day
Rust
AI-Hypercomputer
AI-Hypercomputer
maxtext

A simple, performant, and scalable Jax LLM!

Score
94
โ˜… 2.4k โ‘‚ 550 +3/day
Python
adithya-s-k
adithya-s-k
AI-Engineering.academy

Mastering Applied AI, One Concept at a Time

Score
87
โ˜… 2.3k โ‘‚ 270 +111/day
Jupyter Notebook
dstackai
dstackai
dstack

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Score
86
โ˜… 2.2k โ‘‚ 236 +1/day
Python
kubeflow
kubeflow
trainer

Distributed AI Model Training and LLM Fine-Tuning on Kubernetes

Score
100
โ˜… 2.1k โ‘‚ 983 โ€”
Go
YiVal
YiVal
YiVal

Your Automatic Prompt Engineering Assistant for GenAI Applications

Score
74
โ˜… 2.1k โ‘‚ 328 โ€”
Python
amitshekhariitbhu
amitshekhariitbhu
ai-engineering-interview-questions

Your Cheat Sheet for AI Engineering Interview โ€“ Questions and Answers.

Score
93
โ˜… 2.1k โ‘‚ 384 +36/day
Markdown
eosphoros-ai
eosphoros-ai
DB-GPT-Hub

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

Score
72
โ˜… 2.0k โ‘‚ 250 โ€”
Python
adobe-research
adobe-research
custom-diffusion

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Score
89
โ˜… 2.0k โ‘‚ 141 โ€”
Python
google-deepmind
google-deepmind
penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

Score
75
โ˜… 1.9k โ‘‚ 70 โ€”
Python
THUDM
THUDM
LongWriter

[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Score
71
โ˜… 1.9k โ‘‚ 184 +1/day
Python
ray-project
ray-project
llm-applications

A comprehensive guide to building RAG-based LLM applications for production.

Score
58
โ˜… 1.9k โ‘‚ 255 +1/day
Jupyter Notebook
bespokelabsai
bespokelabsai
curator

Synthetic data curation for post-training and structured data extraction

Score
90
โ˜… 1.7k โ‘‚ 141 โ€”
Python
beam-cloud
beam-cloud
beta9

Ultrafast serverless GPU inference, sandboxes, and background jobs

Score
89
โ˜… 1.7k โ‘‚ 145 โ€”
Go
NVIDIA-NeMo
NVIDIA-NeMo
Curator

Scalable data pre processing and curation toolkit for LLMs

Score
92
โ˜… 1.7k โ‘‚ 296 +1/day
Python
R6410418
R6410418
Jackrong-llm-finetuning-guide
Score
88
โ˜… 1.6k โ‘‚ 255 +21/day
Jupyter Notebook
SakanaAI
SakanaAI
text-to-lora

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

Score
67
โ˜… 1.3k โ‘‚ 86 โ€”
Python
open-edge-platform
open-edge-platform
geti_v2

Build computer vision models in a fraction of the time and with less data.

Score
95
โ˜… 1.3k โ‘‚ 469 +771/day
TypeScript
datadreamer-dev
datadreamer-dev
DataDreamer

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. โ€€ ๐Ÿค–๐Ÿ’ค

Score
63
โ˜… 1.1k โ‘‚ 59 โ€”
Python
louisfb01
louisfb01
start-llms

A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!

Score
78
โ˜… 977 โ‘‚ 127 โ€”
lancedb
lancedb
vectordb-recipes

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

Score
85
โ˜… 966 โ‘‚ 172 โ€”
Jupyter Notebook
lonePatient
lonePatient
Bert-Multi-Label-Text-Classification

This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.

Score
22
โ˜… 923 โ‘‚ 208 โ€”
Python
datawhalechina
datawhalechina
base-llm

ไปŽ NLP ๅˆฐ LLM ็š„็ฎ—ๆณ•ๅ…จๆ ˆๆ•™็จ‹๏ผŒๅœจ็บฟ้˜…่ฏปๅœฐๅ€๏ผšhttps://datawhalechina.github.io/base-llm/

Score
39
โ˜… 880 โ‘‚ 97 +10/day
Jupyter Notebook
nolabs-ai
nolabs-ai
deepfabric

Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline

Score
33
โ˜… 877 โ‘‚ 83 +2/day
Python
theredsix
theredsix
cerebellum

Browser automation system that uses AI-driven planning to navigate web pages and perform goals.

Score
83
โ˜… 862 โ‘‚ 57 โ€”
Python
Oneirocom
Oneirocom
Magick

Magick is a cutting-edge toolkit for a new kind of AI builder. Make Magick with us!

Score
0
โ˜… 841 โ‘‚ 138 โ€”
TypeScript
invergent-ai
invergent-ai
surogate

Training/Fine-tuning at the speed of light

Score
82
โ˜… 807 โ‘‚ 6 +4/day
C++
DaoyuanLi2816
DaoyuanLi2816
can-i-finetune-this

Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.

Score
84
โ˜… 790 โ‘‚ 106 +2/day
Python
IntelLabs
IntelLabs
RAG-FiT

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Score
81
โ˜… 772 โ‘‚ 61 +1/day
Python
AutoArk
AutoArk
TinyEngram

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Score
80
โ˜… 736 โ‘‚ 51 +74/day
Python
netease-youdao
netease-youdao
Confucius4-TTS

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Score
79
โ˜… 655 โ‘‚ 63 +40/day
Python
Denis2054
Denis2054
RAG-Driven-Generative-AI

This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.

Score
69
โ˜… 614 โ‘‚ 214 +1/day
Jupyter Notebook
Related Topics
#llm#python#machine-learning#pytorch#ai#llama#lora#deep-learning#llms#rag#gpt#large-language-models

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly