Stars
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Language model alignment-focused deep learning curriculum
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Source code for the EMNLP 2020 paper "Cold-Start and Interpretability: Turning Regular Expressions intoTrainable Recurrent Neural Networks"
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Model interpretability and understanding for PyTorch
Understanding Deep Networks via Extremal Perturbations and Smooth Masks
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
Magenta: Music and Art Generation with Machine Intelligence
A library of extension and helper modules for Python's data analysis and machine learning libraries.
Efficient Image Captioning code in Torch, runs on GPU
Prepare for programming interviews with pretty practice problems.