-
University of Maryland, College Park
-
07:10
(UTC -05:00) - https://ani0075saha.github.io/
Lists (19)
Sort Name ascending (A-Z)
AI Ethics
Bayesian Deep Learning
Camera-Calibration
CLIP
Coding Tools
Computer Vision
Efficient
Federated Learning
Generative Models
Interview-Prep
LLM
LLM Evaluation
LLM Finetuning
LLM Pretraining
LLM Security
LLM Serving
Multimodal
Privacy
Self-Supervised Learning
Stars
The EYELib: A matlab-python library for Single View Metrology and auto-calibration algorithms and methods
Zero-label image classification via OpenCLIP knowledge distillation
Machine Learning Engineering Open Book
[CVPR 2023] DepGraph: Towards Any Structural Pruning
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
Collection of AWESOME vision-language models for vision tasks
An open source implementation of CLIP.
Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch
Official Jax Implementation of MaskGIT
A high-throughput and memory-efficient inference and serving engine for LLMs
Train transformer language models with reinforcement learning.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
😈Awful AI is a curated list to track current scary usages of AI - hoping to raise awareness
Convert Machine Learning Code Between Frameworks
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
Code and documentation to train Stanford's Alpaca models, and generate the data.
A framework for few-shot evaluation of language models.
LLM training code for Databricks foundation models
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
A unified evaluation framework for large language models
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models
LAVIS - A One-stop Library for Language-Vision Intelligence
Flax is a neural network library for JAX that is designed for flexibility.
Easily compute clip embeddings and build a clip retrieval system with them
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.