open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Raw data, scripts, etc. to produce the tables and figures of our technical report

The Arc project utilizes the power of Kotlin DSL and Kotlin Scripting to define a language optimized for building LLM-powered solutions.

Create-tsi is a generative AI RAG toolkit which generates AI Applications with low code.

Large Language Model Text Generation Inference

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

AIOS: AI Agent Operating System

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

The official implementation of Self-Play Fine-Tuning (SPIN)

GermanRAG - a German dataset for finetuning Retrieval Augmented Generation

Configure netlink interfaces, simple eBPF filters and FRR using Kubernetes resources.

German dataset for DPR model training

Go ahead and axolotl questions

This is the repository for our paper "INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning"

Tools for merging pretrained large language models.

Repository for the EM German Model

A fork containing German benchmark contributions for MTEB, the Massive Text Embedding Benchmark. All contributions will be upstreamed to MTEB.

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

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

Robust recipes to align language models with human and AI preferences

Python tool to support lazy imports.

Philip May’s blog and website project hostet at PhilipMay.com

A blazing fast inference solution for text embeddings models

Machine Learning Toolbox 2

💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Example models using DeepSpeed

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.