Pixxinger

moby

The Moby Project - a collaborative project for the container ecosystem to assemble container-based systems

llama.cpp

LLM inference in C/C++

grok-1

Grok open release

ColossalAI

Making large AI models cheaper, faster and more accessible

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

localGPT

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

llama2.c

Inference Llama 2 in one file of pure C

codellama

Inference code for CodeLlama models

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

search_with_lepton

Building a quick conversation-based search demo with Lepton AI.

oneflow

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

DeepVision

neutron

Neutron is a virtual network service for Openstack.