Parameter-efficient model fine-tuning

GitHub projects using PyTorch, Transformers, and PEFT. Explore 177 indexed GitHub repositories with projects that declare these dependencies together.

177 repositories · 224 projects in our index
87,046

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

agentllmragtutorial
76,052

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

agentaideepseekfine-tuninggemmagptinstruction-tuninglarge-language-modelsllamallama3llmloramoenlppeftqloraquantizationqwenrlhftransformers
58,192

《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

agentagent-memoryai-agentbookcoding-agentcontext-engineeringlarge-language-modelsllmmcpmulti-agentmultimodalragreinforcement-learning
42,611

微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。

agent-frameworkdata-analysisdeep-researchdeep-searchllmsmulti-agent-systemnlppublic-opinion-analysispython3sentiment-analysis
41,430

Making large AI models cheaper, faster and more accessible

aibig-modeldata-parallelismdeep-learningdistributed-computingfoundation-modelsheterogeneous-traininghpcinferencelarge-scalemodel-parallelismpipeline-parallelism
37,347

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

aiassistantchatgptdiscord-botlanguage-modelmachine-learningnextjspythonrlhf
31,167

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

27,152

See, hear, and interact on your local devices.

minicpmminicpm-ominicpm-vmulti-modal
25,077

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

chatbotchatgptfoundation-modelsgpt-4instruction-tuningllamallama-2llama2llavamulti-modalitymultimodalvision-language-modelvisual-language-learning
23,439

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

evaluationhacktoberfesthacktoberfest2025langchainllama-indexllmllm-evaluationllm-observabilityllmopsopen-sourceopenaiplaygroundprompt-engineering
23,286

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

inpaintinglamalatent-diffusionmatpytorchstable-diffusionzits
22,827

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

whisper
22,242

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

beitbeit-3bitnetdeepnetdocument-aifoundation-modelskosmoskosmos-1layoutlmlayoutxlmllmminilmmllmmultimodalnlppre-trained-modeltextdiffusertrocrunilmxlm-e
21,892

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

adapterdiffusionfine-tuningllmloraparameter-efficient-learningpeftpythonpytorchtransformers
19,753

Translate the video from one language to another and embed dubbing & subtitles.

speech-to-textsttsubtitle-translationtext-to-speechttsvideo-transition
19,676

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

16,858

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

15,702

Train your AI self, amplify you, bridge the world

15,387

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

agentaiautomationdata-miningdata-sciencedevelopmentllmresearch
14,820

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

text2music
14,755

Llama中文社区,实时汇总最新Llama学习资料,构建最好的中文Llama大模型开源生态,完全开源可商用

agentllamallama4llmpretrainingrl
...