[CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"

[ECCV2024] This is an official implementation for "PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model"

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

To automate the SLR process and write paper quickly using multi agents of AI

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

SciAssess is a comprehensive benchmark for evaluating Large Language Models' proficiency in scientific literature analysis across various fields, focusing on memorization, comprehension, and analysis.

[AAAI 2024] SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research

[NeurIPS 2023] Official Implementation: "Ambient Diffusion: Learning Clean Distributions from Corrupted Data"

fast-stable-diffusion DreamBooth

Retrieve author and publication information from Google Scholar in a friendly, Pythonic way without having to worry about CAPTCHAs!

A small package to create visualizations of PyTorch execution graphs

Official Pytorch repo of CVPR'23 and NeurIPS'23 papers on understanding replication in diffusion models.

LPIPS metric. pip install lpips

Util functions for learning diffusion models from corrupted data

Tools for merging pretrained large language models.

A full spaCy pipeline and models for scientific/biomedical documents.

Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Minimal Implementation of a D3PM in pytorch

Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance"

Machine Learning Engineering Open Book

Minimalistic large language model 3D-parallelism training

Official Implementation of understanding the latent space of diffusion models through the lens of riemannian geometry (NeurIPS 2023)