Pinned Repositories
apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
chatllama
ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT
ControlNet
Let us control diffusion models!
FlexGen
Throughput-oriented systems for large language models on commodity GPUs.
hypothesis
Hypothesis is a powerful, flexible, and easy to use library for property-based testing.
itree
An Interval Tree Library
minichatgpt
minichatgpt - To Train ChatGPT In 5 Minutes
networkx
Network Analysis in Python
pyllama
LLaMA: Open and Efficient Foundation Language Models
visual-chatgpt
VisualChatGPT
juncongmoo's Repositories
juncongmoo/pyllama
LLaMA: Open and Efficient Foundation Language Models
juncongmoo/chatllama
ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT
juncongmoo/minichatgpt
minichatgpt - To Train ChatGPT In 5 Minutes
juncongmoo/itree
An Interval Tree Library
juncongmoo/ControlNet
Let us control diffusion models!
juncongmoo/networkx
Network Analysis in Python
juncongmoo/visual-chatgpt
VisualChatGPT
juncongmoo/apex
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
juncongmoo/FlexGen
Throughput-oriented systems for large language models on commodity GPUs.
juncongmoo/hypothesis
Hypothesis is a powerful, flexible, and easy to use library for property-based testing.
juncongmoo/metaflow
:rocket: Build and manage real-life data science projects with ease!
juncongmoo/pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
juncongmoo/spconv
Spatial Sparse Convolution Library
juncongmoo/tree
tree is a library for working with nested data structures
juncongmoo/vpt
❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119
juncongmoo/coveragepy
Code coverage measurement for Python
juncongmoo/DeepSpeed-MII
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
juncongmoo/EnergonAI
Large-scale model inference.
juncongmoo/github-readme-stats
:zap: Dynamically generated stats for your github readmes
juncongmoo/OpenChatKit
juncongmoo/SSF
[NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".