s1van

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

imgui

Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

llama

Inference code for Llama models

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

google-research

Google Research

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

babyagi

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

agents

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

awesome-chatgpt

🤖 Awesome list for ChatGPT — an artificial intelligence chatbot developed by OpenAI

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

headshots-starter

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Webpilot

gsgen

[CVPR 2024] Text-to-3D using Gaussian Splatting

knnlm

BlackMamba

Code repository for Black Mamba

falkon

Large-scale, multi-GPU capable, kernel solver

grokking

Neural-Collapse

[NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features

recursive_feature_machines

grokking

Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.

EigenPro2

EigenPro2 iteration in Tensorflow (Keras)

Epoch_wise_Double_Descent

Official implementation of "Multi-scale Feature Learning Dynamics: Insights for Double Descent".

convrfm

Code for convolutional neural feature ansatz and (deep convrfm)

EigenPro

Latest and fastest EigenPro that scales to billions of examples