PeterPham's Projects
llmware RAG Demo App.
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.
A collection of out-of-tree LLVM passes for teaching and learning
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
General technology for enabling AI capabilities w/ LLMs and MLLMs
🤖 Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
Serve 1000s of Fine-Tuned LLMs in Production for the Cost of 1
Simple steps to create an automated folder structure!
Basic Machine Learning Algorithms With Code
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
MagicEdit: High-Fidelity Temporally Coherent Video Editing
Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis
Detect file content types with deep learning
Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexible and interactive visual or linguistic user prompt guidance.
The official repository for MedSAM: Segment Anything in Medical Images.
Teaching LLMs memory management for unbounded context 📚🦙
Memray is a memory profiler for Python
This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.
Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch
Everything about MetaCLIP: curation/training code, metadata, distribution and pre-trained models.
🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
Foundational model for human-like, expressive TTS
MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models
Official implementation for Mini-Gemini