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

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

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

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

stable diffusion webui colab

AirLLM 70B inference with single 4GB GPU

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Using Low-rank adaptation to quickly fine-tune diffusion models.

The official firmware for Meshtastic, an open-source, off-grid mesh communication system.

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

ESP32/ESP8285-based High-Performance Radio Link for RC applications

MQTT gateway for ESP8266 or ESP32 with bidirectional 433mhz/315mhz/868mhz, Infrared communications, BLE, Bluetooth, beacons detection, mi flora, mi jia, LYWSD02, LYWSD03MMC, Mi Scale, TPMS, BBQ thermometer compatibility & LoRa.

基于ChatGLM-6B + LoRA的Fintune方案

⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

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

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

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Generate, animate and schedule your AI characters 🤖

雅意大模型：为客户打造安全可靠的专属大模型，基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM 系列模型，由中科闻歌算法团队研发。(Repo for YaYi Chinese LLMs based on LlaMA2 & BLOOM)

OneTrainer is a one-stop solution for all your Diffusion training needs.

LLM Finetuning with peft

A Unified Library for Parameter-Efficient and Modular Transfer Learning

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！