Niklas

sgpt. SGPT: GPT Sentence Embeddings for Semantic Search

vilio. 🥶Vilio: State-of-the-art VL models in PyTorch & PaddlePaddle

FLAN. Provides a minimal implementation to extract FLAN datasets for further processing

promptsource. Toolkit for creating, sharing and using natural language prompts.

ytclipcc. Create Captions for any YouTube Clip using Wav2Vec2

performers-in-transformers. Performers within 🤗Transformers!

kto. Python

sentence-transformers. Multilingual Sentence & Image Embeddings with BERT

megablocks. Python

matrixshapes. Language modelling task to infer shapes of matrices - One of the most difficult tasks for models like GPT-3, GPT-J

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

MNIST-algorithms. Comparing simple deep learning models on MNIST - CNN, MLP, VIT

CS50. Computer Science Course taught at Harvard

CS50xAI. AI-specialization of CS50

prompt_semantics. This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”

hf-translation-benchmark. Benchmark the best translation models out there on Performance, Speed & Memory.

CS231n. CS231n at Stanford University