[EMNLP 2024 Findings] ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming

A course on aligning smol models.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

This repository contains the code for Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics (MICCAI'24)

LPIPS metric. pip install lpips

Bringup-Bench is a collection of standalone minimal library and system dependence benchmarks useful for bringing up newly designed CPUs, accelerators, compilers and operating systems. You probably …

A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

Resources about Sign Language Processing (e.g., Sign Language Recognition / Translation / Production)

CAMEL-Bench is an Arabic benchmark for evaluating multimodal models across eight domains with 29,000 questions.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Ultralytics YOLO11 🚀

EVA Series: Visual Representation Fantasies from BAAI

1.4B latent diffusion model fine tuning

LLM inference in C/C++

Example project demonstrating automatic restarts and session management for long-running tasks in SLURM using Python. Features signal handling, state persistence with dill, and job resubmission logic.

A GPipe implementation in PyTorch

Training and serving large-scale neural networks with auto parallelization.

Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".

[InterSpeech 2024] Official code repository of paper titled "Bird Whisperer: Leveraging Large Pre-trained Acoustic Model for Bird Call Classification" accepted in InterSpeech 2024 conference.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Scenic: A Jax Library for Computer Vision Research and Beyond

Segment Anything in Medical Images

A simple and efficient Mamba implementation in pure PyTorch and MLX.