Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

Can LLMs Learn by Teaching? A Preliminary Study

The codebase of our paper "Improving the Training of Rectified Flows"

The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in th…

Official implementation of Cold-Diffusion for different transformations in pytorch.

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

The official Meta Llama 3 GitHub site

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

Geometric Computer Vision Library for Spatial AI

DSPy: The framework for programming—not prompting—foundation models

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

🐚 OpenDevin: Code Less, Make More

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…

SudoLang LLM Support for VSCode

⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

Open-Sora: Democratizing Efficient Video Production for All

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

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

[ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Example task UIs for Amazon SageMaker Ground Truth

A guidance language for controlling large language models.

ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Code Repository of Evaluating Quantized Large Language Models

This is the code that went into our practical dive using mamba as information extraction

Mamba SSM architecture