unsloth

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline

Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.

A framework for agentic tool use training with reinforcement learning

Upload your data → Get a fine-tuned SLM. Free.

LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman

Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.

An implementation of GRPO for Unsloth's VLMs training

从对话数据到训练:数字分身 + 模型蒸馏 From Dialogue Data to Training Closed-Loop: Digital Twin + Model Distillation

本项目利用医学领域的 CoT 数据对 Deepseek-R1-Distill-Qwen-7B 进行微调，通过 QLoRA 量化和 Unsloth 加速训练，显著提升模型在复杂医学推理任务中的慢思考能力。知识蒸馏技术使轻量级模型获得大模型的推理优势，实现高效、准确且具有解释性的医学问答系统。

Natural language control for Python CLI tools using locally-trained SLMs (CPU inference)

Powerful no-code LLM fine-tuner: upload data → train → deploy in minutes. Unsloth 2-5× acceleration · QLoRA/DPO/RLHF/PPO/ORPO · Reward Model training · GGUF export · vLLM inference · BLEU/ROUGE/BERTScore · full CLI · Heretic Mode to unlock full model potential

Local-first desktop assistant for the whole job hunt — scrape listings, match with a local LLM, generate applications in your own voice, and track everything on a Kanban board.

Produced by号角工作室/适用于Windows11与WSL2的针对Intel Arc独显的Unsloth的微调问题修复 Produced by Horn Studio / Unsloth Fine-Tuning Fixes for Intel Arc dGPUs on Windows 11 & WSL2

LLM finetuning for Sudoku solving

Finetune Web UI is a user-interface for training and deploying pre-trained models.

Low-Resource LLM Fine-Tuning using Unsloth and LoRA/QLoRA (WSL2/Linux) 🧠

Adversarial LLM arena using GRPO + SFT to train a model that generates questions hard LLMs can't solve

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.