OSS AI Projects - simon-oz/Weekly-AI-news GitHub Wiki
AgentGPT - Assemble, configure, and deploy autonomous AI Agents in your browser.
Alpaca-Lora - Instruct-tune LLaMA on consumer hardware
ATTemplate - a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
CodeT5+ - Open Code LLMs for Code Understanding and Generation
Databricks Dolly-v2 - a large language model trained on the Databricks Machine Learning Platform
espnet - End-to-End Speech Processing Toolkit
Falcon 40 Instruct & Falcon 40b/TII - is a 40B parameters causal decoder-only model built by TII and trained on 1,000B tokens of RefinedWeb enhanced with curated corpora.
GOAT - a Fine-tuned LLaMA that is Good at Arithmetic Tasks
Gorilla - Gorilla: An API store for LLMs
GPT4All - an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
GPT-Researcher - GPT based autonomous agent that does online comprehensive research on any given topic
H2oGPT - Private Q&A and summarization of documents+images or chat with local GPT, 100% private, Apache 2.0. Supports LLaMa2, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/
Infinigen/Princeton-VL - Infinite Photorealistic Worlds using Procedural Generation
Koala - EasyLM - is a language model fine-tuned on top of LLaMA. Blog
LangChain - Building applications with LLMs through composability
Lit-Parrot - Implementation of the StableLM/Pythia/INCITE language models based on nanoGPT. Supports flash attention, LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
LLaMA - Inference code for LLaMA models, NO TRAINING CODE
LLaMA2-Webui - Run Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Supporting Llama-2-7B/13B/70B with 8-bit, 4-bit. Supporting GPU inference (6 GB VRAM) and CPU inference.
LLaMA_Index - a data framework for your LLM applications
Megatron - Nvidia - Ongoing research training transformer models at scale
MiniChain - A tiny library for coding with large language models.
LMFlow - An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
MosaciML-Foundry - LLM training code for MosaicML foundation models MPT-7B
MTEB - Massive Text Embedding Benchmark -
oobabooga / text-generation-webui - A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
OpenLLaMA Openlm-research - a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
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.
PandaGPT - One Model To Instruction-Follow Them All
PineCone - The vector database for machine learning applications. Build vector-based personalization, ranking, and search systems that are accurate, fast, and scalable.
privateGPT - Interact privately with your documents using the power of GPT, 100% privately, no data leaks
sealion - a family of open source language models developed by AI Singapore to better understand and represent the diverse contexts, languages, and cultures of Southeast Asia (SEA).
Stable Diffusion Weibu - Stable Diffusion web UI A browser interface based on Gradio library for Stable Diffusion.
Stanford-Alpaca - Code and documentation to train Stanford's Alpaca models, and generate the data.
StarCoder - a language model (LM) trained on source code and natural language text. StarCode+ is an updated version.
TigerBot - Chinese version LLM, 7B and 180B
trlx - A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Vicuna FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
vllm UC Berkeley - A high-throughput and memory-efficient inference and serving engine for LLMs
WizardCoder - Empowering Code Large Language Models with Evol-Instruct WizardLM nlpxucan - Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder