spb/tools-spboucher-ai

1{2  "slug": "unsloth",3  "name": "Unsloth",4  "aliases": ["unsloth (PyPI)", "Unsloth Studio", "Unsloth Desktop"],5  "vendor": { "name": "Unsloth AI", "slug": "unsloth-ai", "website": "https://unsloth.ai/docs" },6  "homepage_url": "https://github.com/unslothai/unsloth",7  "docs_url": "https://unsloth.ai/docs",8  "repo_url": "https://github.com/unslothai/unsloth",9  "license_url": "https://github.com/unslothai/unsloth/blob/main/LICENSE",10  "product_type": "framework",11  "product_status": "active",12  "summary": "Open-source framework for fine-tuning and running LLMs with reduced memory, covering LoRA, QLoRA, full fine-tuning and RL, GGUF export, Dynamic quantizations and a local Studio/Desktop UI",13  "description": "Unsloth is an Apache-2.0 framework for training and running language models on your own hardware with lower memory use than stock implementations, achieved through hand-written kernels and optimized attention paths. It supports LoRA, QLoRA and full fine-tuning, continued pretraining, and reinforcement-learning methods such as GRPO and DPO, extending beyond text to diffusion, text-to-speech and embedding models, with FP8 training on supported GPUs. Trained models export to GGUF, NVFP4, FP8 and other formats for llama.cpp-style runtimes, and the team publishes widely used \"Dynamic\" GGUF quantizations of popular open models.\n\nIn 2026 the project added Unsloth Studio, a browser-based UI, and Unsloth Desktop, a native app for macOS, Windows and Linux installable through Homebrew or WinGet, which run and train models locally and serve them through an OpenAI-compatible API; `unsloth start` connects coding agents such as Claude Code or Codex to those local models, and Data Recipes build datasets from PDFs, CSVs and DOCX files. Platform support covers NVIDIA, AMD and Intel GPUs, CPU and a Docker image, with free Colab notebooks as the traditional on-ramp. The main site blocks automated clients, and the fast release pace sometimes breaks dependencies between Unsloth, Transformers and PyTorch versions, so pinning matters.",14  "capabilities": ["LoRA, QLoRA, full fine-tuning and continued pretraining", "RL methods including GRPO and DPO; FP8 training", "Diffusion, TTS and embedding model training", "Export to GGUF, NVFP4 and FP8; Dynamic GGUF quantizations", "Unsloth Studio web UI and Desktop app for macOS, Windows and Linux", "OpenAI-compatible local serving and agent connection via `unsloth start`", "Data Recipes for building datasets from documents"],15  "workflows": ["Fine-tune an open model with QLoRA on a single GPU and export to GGUF for Ollama", "Run GRPO reinforcement learning on a reasoning task", "Serve a local model to Claude Code through the Desktop app"],16  "advantages": ["Lower memory and faster training than stock pipelines", "Apache-2.0 license", "Smooth export path to local runtimes"],17  "limitations": ["Version coupling with Transformers and PyTorch", "Main website rejects automated clients", "Best performance still requires NVIDIA GPUs"],18  "prerequisites": ["Python with PyTorch and a supported GPU, or the Desktop app", "Hugging Face access for base models"],19  "audiences": ["Researchers and students fine-tuning open models on limited hardware", "Developers producing quantized models for local deployment"],20  "alternatives": ["axolotl", "transformers", "mlx-lm", "pytorch"],21  "categories": [{ "slug": "model-training", "primary": true }, { "slug": "local-inference", "label": "Studio/Desktop local serving" }],22  "tags": ["fine-tuning", "open-source", "python", "llm", "quantization", "gguf", "desktop"],23  "use_cases": ["fine-tune-models", "run-local-models"],24  "operating_systems": ["linux", "macos", "windows"],25  "execution_modes": ["local", "self-hosted"],26  "interfaces": ["library", "cli", "desktop", "web", "api"],27  "deployment_models": ["embedded", "desktop"],28  "integrations": ["Hugging Face Transformers", "PyTorch", "llama.cpp", "Ollama", "vLLM", "Claude Code", "Google Colab", "Docker"],29  "data_formats": ["Safetensors", "GGUF", "NVFP4", "JSONL", "PDF/CSV/DOCX (Data Recipes)"],30  "languages": ["Python"],31  "source_model": "open-source",32  "license_spdx": "Apache-2.0",33  "pricing_model": ["open-source", "free"],34  "self_hostable": true,35  "sources": [36    { "url": "https://github.com/unslothai/unsloth", "type": "official_site", "title": "unslothai/unsloth", "supports": ["name", "summary", "capabilities"], "checked_at": "2026-11-02", "note": "unsloth.ai root returns 403 to automated clients; the repository is used as homepage" },37    { "url": "https://unsloth.ai/docs", "type": "official_docs", "title": "Unsloth documentation", "supports": ["capabilities", "operating_systems", "interfaces"], "checked_at": "2026-11-02" },38    { "url": "https://github.com/unslothai/unsloth/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" }39  ],40  "confidence": "high",41  "uncertainty_note": "The documentation does not describe paid tiers; pricing_model reflects the open-source software only. unsloth.ai itself could not be loaded by automated clients.",42  "discovery_method": "editorial-research",43  "depth": "standard",44  "editorial_status": "reviewed",45  "visibility": "public",46  "featured": false,47  "author": "batch-A"48}49