lora

A local-first workspace that keeps your generated media connected to the prompts, models and workflows that created them. Search, compare and send anything straight back into ComfyUI — nothing leaves your machine.

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

Phi-3, -3.5, and -4 for Mac: Locally-run Vision and Language Models for Apple Silicon

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.

The cleanest, responsive AI workspace. Run highly tuned image and video workflows flawlessly from your desktop or your phone. Built on ComfyUI.

(AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questions

Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset

The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"

AI character studio on a node canvas. Build consistent characters, train LoRAs, and generate on your own GPU.

Enhancing LLMs with LoRA

Krea 2 & Klein 9B LoRA - LoKR Studio — train, profile, repair, and extract Krea 2, Flux 2 Klein 9B & MiniMax LoRAs & LoKRs

Self-hosted, one-tab workbench for the whole LoRA lifecycle: build Character / Concept / Style datasets (generate from a reference, scrape, or triage a huge dump in the Image Bank), curate, caption, clean watermarks, train locally or in the cloud across five model families, then rank checkpoints in a Test Studio. Free & local.

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

⚡ Zero-Stall MoE Inference via Lookahead Prediction & Async DMA Prefetching. Optimized for SSD I/O with Hybrid MLA+Sliding Window Attention.

Agentic AI 智能体开发实战

Implementation of HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

Gradio wrapper for sd-scripts by kohya

MESH-API — Off-Grid AI & API Router & with MCP server & over 30 API extensions for Meshtastic & MeshCore - Seamlessly connect LM Studio, Ollama, AI Providers , 3rd-party APIs, Agents & Home Assistant to your LoRa mesh. Supports custom commands, Twilio SMS, Discord channel routing, & GPS emergency alerts via SMS, email, or Discord + SO MUCH MORE

M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.

AI-assisted media curator for large image/video datasets. Streamlined captioning, cropping, masking for LoRA/diffusion training workflows.