Awesome Opensource Ai

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

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

LlamaIndex is the document processing platform for AI

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

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

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

Go ahead and axolotl questions

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

Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!

Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

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

AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.

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

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

Synthetic data curation for post-training and structured data extraction