NouamaneTazi

AutoGPT

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.

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

gpt-pilot

The first real AI developer

generative-models

Generative Models by Stability AI

awesome-free-chatgpt

🆓免费的 ChatGPT 镜像网站列表，持续更新。List of free ChatGPT mirror sites, continuously updated.

Grounded-Segment-Anything

Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

OpenLLM

Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint, locally and in the cloud.

ml-ferret

axolotl

Go ahead and axolotl questions

promptbase

All things prompt engineering

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

fully-local-pdf-chatbot

Yes, it's another chat over documents implementation... but this one is entirely local!

communitynotes

Documentation and source code powering Twitter's Community Notes

segment-anything-fast

A batched offline inference oriented version of segment-anything

benchmark

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

flash-fft-conv

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

IndicTrans2

Translation models for 22 scheduled languages of India

LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

discord-bots

drawIT

Automate creation of diagrams.

Finetuning-of-Llama-2-7b-using-QLoRA

- Finetuning Llama-2-7b using QLoRA using TinyStories dataset - This finetuning was conducted on the free version of Google collab with less than 15 Gb VRAM thanks to QLora and Parameter-Efficient Fine-Tuning.

Easy-Finetuning-of-Llama-2-7b-using-QLoRA

Finetuning Llama-2-7b using QLoRA using TinyStories dataset

autogen-experiments

llama-index-docs

whisper-llm-gtts

Moroccan-Arabic-Normalization