#
Starred repositories
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)
Implementing soft terminology constraints in NMT by annotating NMT source-side training data with target-side terminology
🔎 Open source distributed and RESTful search engine.
Fast inference engine for Transformer models
Training open neural machine translation models
Retrieval and Retrieval-augmented LLMs
Code implementation for Findings of EMNLP 2023 paper "Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment"
[CVPR 2023 (Highlight)] FAME-ViL: Multi-Tasking V+L Model for Heterogeneous Fashion Tasks
[NeurIPS 2023] SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization
Official PyTorch Implementation for Fast Adaptive Multitask Optimization (FAMO)
Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)
Curated tutorials and resources for Large Language Models, AI Painting, and more.
A collaborative project to collect datasets in SEA languages, SEA regions, or SEA cultures.
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
A Library for Advanced Deep Time Series Models.
The official implementation of Achieving Cross Modal Generalization with Multimodal Unified Representation (NeurIPS '23)
ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.
This code accompanies the the paper Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture (https://arxiv.org/pdf/2112.08534.pdf).
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
Approaching (Almost) Any Machine Learning Problem
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.