matbee's repositories
generate-multiview-images
Repository for automating the capturing of multi-view images of 3d models
React-3DObject-From-Image
Experimenting with Three.JS + SAM2 + Stable-Fast-3D
onnx-image-upscaling
Supporting image upscaling models in onnx
anynode
A Node for ComfyUI that does what you ask it to do
subtitler
Free on-device web app for audio transcribing and rendering subtitles
llm-scraper
Turn any webpage into structured data using LLMs
WeblinxRePlaywrightBrowser
Browser Automation with Weblinx and Playwright
LLM-Finetuning-Workspace
Scripts to be used for finetuning LLMs on my dual gpu setup
linux-desktop-usage-tracking
Multimodal Language Model prompting using active Linux desktop screens as input
istft-onnx
Export an ONNX graph that performs ISTFT. Designed for TTS models.
webllama
Llama-3 agents that can browse the web by following instructions and talking to you
reader
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
typescript-project-text-splitter
Split your typescript/javascript project for training on your codebase.
webpack-plugin-knowledge-graph
Generate a comprehensive knowledge graph of your code base to aid in RAG
resemble-denoise-onnx-inference
Inference of Resemble Denoiser in onnxruntime-web
eslint-plugin-max-tokens
Enforces max tokens for your code to enable better LLM training on your private code base
webpack-plugin-embedding-generator
Automatically generate embeddings for each part of your code base to enable RAG and sharing of your pre-computed embeddings as an API
ollama
Get up and running with Llama 2, Mistral, and other large language models.
guidance
A guidance language for controlling large language models.
continue
⏩ Continue is an open-source autopilot for VS Code and JetBrains—the easiest way to code with any LLM
stable-diffusion-docker
Docker image for Stable Diffusion WebUI with ControlNet, After Detailer, Dreambooth, Deforum and roop extensions, as well as Kohya_ss and ComfyUI
UnofficialMetaHumanVR_Studio
A template for creating your own MetaHuman VR shows
winfsp
Windows File System Proxy - FUSE for Windows
sherpa-onnx
Real-time speech recognition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go
whisper_streaming
Whisper realtime streaming for long speech-to-text transcription and translation