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

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

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

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

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

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

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

Go ahead and axolotl questions

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

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

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

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

Easily build AI systems with Evals, RAG, Agents, fine-tuning, synthetic data, and more.

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

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

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

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

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

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

OML 1.0 via Fingerprinting: Open, Monetizable, and Loyal AI