Tonic's Projects
Segment Anything for Microscopy
[CVPR 2024] "MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis" (Official Implementation)
A fast local neural text to speech engine for Mycroft
proof of concept prototype for generating and querying against a large knowledge graph with ai
AI-Assisted Firewall for Cognitive Integrity
Official implementation for Mini-Gemini
Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines
Code for Medium blog posts
Tensorflow implementation of MIRNet for Low-light image enhancement
MistralMED outshines other language models when it comes to answering complex medical questions, providing accurate and powerful insights for researchers.
Machine Learning Engineering Open Book
A high performance data access library for machine learning tasks
This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024
The official codes for "Towards Building Multilingual Language Model for Medicine"
Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
Implementation of MobileViT in TensorFlow and Keras
ModelScope: bring the notion of Model-as-a-Service to life.
The Mojo Programming Language
Automate Creation of YouTube Shorts using MoviePy.
Montelo is the LLM developer platform for TypeScript.
Paper describing "Morpheus - A Network For Powering Smart Agents"
forcomming community morpheus node :-)
A universal language for business and technology
A Streamilt web app for music source separation & karaoke
Morpheus Request for Comments
Multimed - accessible multimodal app ( Fuyu , Stable LM , Seamless m4t , multi media input in, audio and text out.
an accessible gradio interface with a jailbreak GPT4-V prompt and using seamless M4T built with vectara embeddings
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.