-
University of Amsterdam
- Amsterdam
- https://github.com/thongnt99
- @thongnt99
Highlights
- Pro
Block or Report
Block or report thongnt99
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Visual Delta Generator with Large Multi-modal Model for Semi-supervised Composed Image Retrieval - CVPR2024
An open source implementation of CLIP.
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
A library for mechanistic interpretability of GPT-style language models
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
A high-throughput and memory-efficient inference and serving engine for LLMs
Data release for the ImageInWords (IIW) paper.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Official software repository of S. Bruch, F. M. Nardini, C. Rulli, and R. Venturini, "Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations". Long Paper @ ACM SIG…
the AI-native open-source embedding database
Fast and memory-efficient exact attention
This is the official repository for Retrieval Augmented Visual Question Answering
Implementation of "Efficient Multi-vector Dense Retrieval with Bit Vectors", ECIR 2024
ImageBind One Embedding Space to Bind Them All
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Taming Transformers for High-Resolution Image Synthesis
LaQuE: Large-Scale Query Collection for Entity Search
LUKE -- Language Understanding with Knowledge-based Embeddings
A fast, efficient universal vector embedding utility package.
Framework for evaluating ANNS algorithms on billion scale datasets.
This is the official repository of F. M. Nardini, C. Rulli, S. Trani, R. Venturini, "Distilled Neural Networks for Efficient Learning to Rank". IEEE TKDE. 2022.
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.