Build AI Assistants with memory, knowledge and tools.

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frame…

Machine Learning Engineering Open Book

Code accompanying "How I learned to start worrying about prompt formatting".

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

prompt2model - Generate Deployable Models from Natural Language Instructions

An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.

An open-source tool-augmented conversational language model from Fudan University

[CVPR 2024] OneLLM: One Framework to Align All Modalities with Language

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

Debug PyTorch code using PySnooper

Generate textbook-quality synthetic LLM pretraining data

Neural question generation using transformers

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Transformer related optimization, including BERT, GPT

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Code written with pytorch for model QA-CNN, QA-biLSTM, AP-CNN, AP-biLSTM based on paper "Attentive pooling networks"

VisualBERT implementation using Huggingface and PyTorch-Lightning for memes classification with the use of both text and images

Research code for the paper "Fine-tuning wav2vec2 for speaker recognition" found at https://arxiv.org/abs/2109.15053

TensorFlow implementation of "Multimodal Speech Emotion Recognition using Audio and Text," IEEE SLT-18

Scripts used in the research described in the paper "Multimodal Emotion Recognition with High-level Speech and Text Features" accepted in the ASRU 2021 conference.

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps[AAAI2021]

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

Reading list for research topics in multimodal machine learning

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

A framework that facilitates flexible natural language parsing. Currently used as a foundation for other projects.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Practical Deep Learning at Scale with MLFlow, published by Packt