Browse the directory

Free open-source, config-driven LLM fine-tuning framework covering full and parameter-efficient fine-tuning (LoRA, QLoRA), preference tuning (DPO, KTO, ORPO), and reinforcement learning across many model families through declarative YAML configs.

Official Hugging Face Agent Skills collection for Claude Code, Codex, Cursor, Gemini CLI, and other skills-compatible agents, covering Hub CLI workflows, datasets, model search, Spaces, Gradio, fine-tuning, evaluations, local models, papers, Trackio, ZeroGPU, transformers.js, TRL, and the Hugging Face MCP server.

Apache-2.0 library for running raw PyTorch training and inference code across CPU, GPU, TPU, DeepSpeed, FSDP, and mixed-precision environments.

Apache-2.0 library for loading, sharing, streaming, inspecting, and preprocessing AI datasets from the Hugging Face Hub or local files.

Apache-2.0 model-definition framework for pretrained text, vision, audio, video, and multimodal models across inference, training, pipelines, generation, and fine-tuning.

Guide to pinning Claude Code plugin dependency versions, semver constraints, upgrade testing, and preventing surprise behavior changes during team rollouts.

Apache-2.0 library for pretrained diffusion model pipelines, schedulers, adapters, optimization, and training workflows for image, video, and audio generation in PyTorch.

Apache-2.0 library for parameter-efficient fine-tuning of large pretrained models with adapters, LoRA, prompt tuning, Transformers, Diffusers, and Accelerate.

Open-source library for fast, memory-efficient fine-tuning, reinforcement learning, and training of open LLMs — train 500+ models up to 2x faster with up to 70% less VRAM and no accuracy loss, with LoRA/QLoRA support and export to GGUF, safetensors, vLLM, and Ollama.

Microsoft open-source Model Context Protocol curriculum with hands-on MCP server, client, security, transport, auth, deployment, Azure, VS Code, Inspector, PostgreSQL, and cross-language examples.

Apache-2.0 distributed AI compute engine for scaling Python, ML data processing, training, tuning, reinforcement learning, and model serving workloads.

Official Perplexity MCP server that connects Claude to the Perplexity Sonar API for real-time, web-grounded answers with citations, so responses can draw on current information beyond the model's training data.

Apache-2.0 Python framework from Hugging Face for dense embeddings, sparse embeddings, semantic search, reranking, multimodal retrieval, and embedding-model training.

The Claude Code data-handling controls that matter for teams working near PHI: no-training commercial policy, retention windows, Zero Data Retention, encryption, local transcript handling, telemetry opt-outs, and security model.