Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

python agent text-to-speech ui reinforcement-learning ai self-hosted tts openai image-generation llama gemma fine-tuning llm stable-diffusion llms chatgpt qwen deepseek unsloth

• Updated Nov 12, 2026
• Python

Hundreds of models & providers. One command to find what runs on your hardware.

skill mlx llm localai gguf unsloth

• Updated Nov 12, 2026
• Rust

250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.

unsloth

• Updated Nov 12, 2026
• Jupyter Notebook

nlp machine-learning guide pytorch dataset openai fine-tuning llm qwen deepseek unsloth llama3

• Updated Nov 3, 2026
• Jupyter Notebook

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.

macos machine-learning text-to-speech deep-learning transformers speech-recognition speech-to-text lora whisper mlx peft huggingface on-device-ai apple-silicon large-language-models llm vision-language-model local-llm llm-finetuning unsloth

• Updated Jun 23, 2026
• Python

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

python open-source data-science machine-learning ai open evaluation source dataset agents synthetic synthetic-data fine-tuning distillation huggingface huggingface-datasets unsloth

• Updated Nov 6, 2026
• Python

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.

transformer lora fine-tuning sft dpo huggingface apple-silicon rlhf qlora unsloth grpo claude-code gaslamp

• Updated Jun 28, 2026
• Python

A framework for agentic tool use training with reinforcement learning

reinforcement-learning fine-tuning dpo tool-use langchain llm-agents unsloth agentic-ai smolagents grpo

• Updated Apr 8, 2026
• Python

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

open-source machine-learning fine-tuning slms llm llms unsloth

• Updated Jul 18, 2026
• Python

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

style-transfer lora gemma caveman fine-tuning llm qlora unsloth

• Updated Jul 9, 2026
• Python

WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

threejs typescript pytorch wargaming mission-control command-and-control next-js situational-awareness fastapi react-three-fiber operational-technology glassmorphism local-llm qwen defence-technology unsloth ai-simulation military-simulation tactical-visualization tactical-simulation

• Updated Nov 12, 2026
• HTML

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

open-source text-generation lora fine-tuning rag huggingface llm chromadb local-ai llm-finetuning unsloth

• Updated Mar 21, 2026
• Python

An implementation of GRPO for Unsloth's VLMs training

reinforcement-learning vlm huggingface trl unsloth grpo grpotrainer

• Updated Aug 7, 2025
• Python

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

ai chatbot openai finetune open-ai digital-twin distill huggingface personal-ai llm ai-avatar qlora qwen finetune-llm unsloth 4o

• Updated Mar 19, 2026
• Python

Code for Deep Learning for Modern AI

deep-learning mnist neural-networks llama quantization clip bert diffusion distillation multimodal llms dreambooth unsloth llama3 dreambooth-finetuning

• Updated Apr 23, 2026
• Jupyter Notebook

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。

nlp ai lora medical-application distillation llm chain-of-thought qlora qwen unsloth deepseek-r1 4-bit-quantization

• Updated Mar 10, 2025
• Python

Fine-tuned Qwen2-VL-7B for LaTeX OCR using LoRA and Unsloth on the LaTeX OCR dataset. Built augmentation pipeline (rotation, noise, contrast jitter), ran LoRA rank sweep (r=8/16/32), and evaluated across CER, Token F1, BLEU-4, and Exact Match. Deployed as a Gradio Space with live metric computation.

ocr latex computer-vision deep-learning transformers lora gradio fine-tuning qwen2 unsloth

• Updated Jun 25, 2026
• Jupyter Notebook

Custom model training using modern architectures. 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs. Published adapter on HuggingFace. From training pipeline to deployed model.

open-source transformers colab lora gradio 4bit alpaca peft finetuning huggingface llm instruction-tuning qlora unsloth llama3

• Updated Apr 2, 2026
• Jupyter Notebook

No-code LLM fine-tuning: upload your data → click Train → get a model you can run anywhere. Gradio UI + CLI · SFT/DPO/ORPO/KTO/GRPO/reward models · distillation, vision & embedding models · Unsloth 2-5× · QLoRA · multi-GPU (FSDP/DeepSpeed) · GGUF/FP8 export · vLLM & llama.cpp serving · benchmarks & LLM-judge eval · Heretic Mode

python ai gradio fine-tuning peft dpo trl llm llms local-llm local-ai ollama lm-studio gguf unsloth abliteration

• Updated Nov 7, 2026
• Python

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

nlp machine-learning slm quantization gemma fine-tuning cli-tools local-first llm llama-cpp qlora unsloth

• Updated Nov 9, 2026
• Python