finetune

AirLLM 70B inference with single 4GB GPU

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

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

CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/SaaS solutions, with features comparable to Hugging Face. Gain full control over the lifecycle of LLMs, datasets, and agents, with Python SDK compatibility with Hugging Face. Join us! ⭐️

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

企业级稳定的OpenAI、Claude、Gemini等的API接口-For企业和开发者。OpenAI的api proxy，支持ChatGPT的API调用，支持Anthropic claude的官方接口形式，支持Google gemini的官方接口形式，支持：gpt-5，sora。不需要openai Key, 不需要买openai的账号，不需要美元的银行卡，通通不用的，直接调用就行，稳定好用！！智增增

simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

Fine-tuning code for CLIP models

FineTune LLMs in few lines of code (Text2Text, Text2Speech, Speech2Text)

Implementation of HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

Gradio wrapper for sd-scripts by kohya

从对话数据到训练:数字分身 + 模型蒸馏 From Dialogue Data to Training Closed-Loop: Digital Twin + Model Distillation

Create synthetic datasets for training and testing Language Learning Models (LLMs) in a Question-Answering (QA) context.

Awesome List of Vision Language Prompt Papers

Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!

Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.

This repository not only contains experience about parameter finetune, but also other in-practice experience such as model ensemble (boosting, bagging and stacking) in Kaggle or other competitions.

Physics Master is a model fine-tuned from llama3-8B-Instruct. It can answer your physics question!

A repository of technical articles on AI algorithms, model finetuning, AI agents, open-source libraries, and system design. Perfect for researchers and enthusiasts looking for in-depth insights.