Bitwarden Secrets Manager SDK.

The toolkit can be used for creating a mixture from models or from adapters.

Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Scalable data pre processing and curation toolkit for LLMs

Development Version of the CRAN OneMapSg API CRANR Package

A Comparative Framework for Multimodal Recommender Systems

A framework for few-shot evaluation of language models.

Benchmarking LLM for Malay tasks.

Multilingual Large Language Models Evaluation Benchmark

Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image …

Port of Facebook's LLaMA model in C/C++

Web archiving tools on Hadoop

What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets

Tools for merging pretrained large language models.

Examples in the MLX framework

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA.

Web archiving utility library