Popular GitHub Repositories for Fine Tuning

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

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! ?

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

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

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

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

? ????? about ????, ??????, and ?????? ??? for free by designing, training, and deploying a real-time financial advisor LLM system ~ ?????? ???? + ????? & ??????? ?????????

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

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

Build, customize and control you 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

Your Automatic Prompt Engineering Assistant for GenAI Applications

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

WebUI for Fine-Tuning and Self-hosting of Open-Source Large Language Models for Coding

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

dstack is a lightweight, open-source alternative to Kubernetes & Slurm, simplifying AI container orchestration with multi-cloud & on-prem support. It natively supports NVIDIA, AMD, TPU, and Intel accelerators.

Distributed ML Training and Fine-Tuning on Kubernetes

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

:dart: Task-oriented embedding tuning for BERT, CLIP, etc.