Language Models

AnimatedLLM uses animations to explain the mechanisms behind large language models.

Sagify describes its project as a way to work with large language models and machine learning more easily.

DeepSpeed provides optimization tools that make distributed deep learning training more efficient.

ANEE wraps pretrained transformer inference with an energy budget and early exits inside model execution.

SWE-bench evaluates whether language models can resolve real GitHub issues.

GPTGames provides an open-source browser collection of small games and utilities generated mostly by language models.

PowerInfer supports serving large language models for local deployment and inference.

FinetuneDB explains current practices for evaluating large language model outputs and structuring the evaluation process.

Upstage builds large language models and document-processing engines for workplace workflows.

OptiMate is a collection of libraries for optimizing AI model performance; the repository is marked as a legacy project.

FastChat offers an open platform for training, serving, and evaluating large language models, and hosts release repositories for Vicuna and Chatbot Arena.

LocalAI runs text, voice, vision, image, video, and agent workloads through an open-source AI engine.

GroqChat provides a browser-based chat interface for Groq language models, with conversation history, URL attachments, and speech-to-text.

An interactive chart tracks the rise of large language models such as ChatGPT, Bing Chat, LaMDA, LLaMA, and PaLM.

DeepSeek-VL2 supports multimodal understanding through a mixture-of-experts vision-language model.

traceAI provides open source tracing for AI applications and frameworks using OpenTelemetry.

An open dataset with 30 trillion tokens for training Large Language Models.

Sequoia Capital surveys how large language models enable machines to write, code, draw, and create.

Petals runs large language models across distributed computers and supports fine-tuning and inference.

Agency provides a Go library for developers building applications with large language models.

bitsandbytes enables large language models in PyTorch using k-bit quantization.

PocketPal AI brings language models to a phone, providing a mobile app for interacting with models on Android.

Helicone provides open-source observability for LLM applications, with tools to monitor, evaluate, and experiment.

Run the llm command-line tool to access and work with large language models from a terminal.