ZakiAIDev

awesome-chatgpt-prompts

This repo includes ChatGPT prompt curation to use ChatGPT better.

llm.c

LLM training in simple, raw C/CUDA

uv

An extremely fast Python package and project manager, written in Rust.

dask

Parallel computing with task scheduling

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

awesome-generative-ai-guide

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

metaflow

Open Source Platform for developing, scaling and deploying serious ML, AI, and data science systems

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

intermediatePython

borb

borb is a library for reading, creating and manipulating PDF files in python.

mistral-finetune

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

fastapi-tips

FastAPI Tips by The FastAPI Expert!

semantic-router

Superfast AI decision making and intelligent processing of multi-modal data.

aici

AICI: Prompts as (Wasm) Programs

llm-datasets

High-quality datasets, tools, and concepts for LLM fine-tuning.

nanotron

Minimalistic large language model 3D-parallelism training

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

lilac

Curate better data for LLMs

prometheus

[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score rubric, Prometheus is a good alternative for human evaluation and GPT-4 evaluation.

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters

ViT-CoMer

Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions.

langcheck

Simple, Pythonic building blocks to evaluate LLM applications.

RAGElo

RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker

url

Uncertainty-aware representation learning (URL) benchmark

senior-python-engineer

Advanced Python for Senior Software Engineers • Design Patterns • S.O.L.I.D • OOP • Concurrency • Python Libraries

Ada-LEval

The official implementation of "Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks"

genai-llm-application-monitoring-on-aws

pre-commit-heaven

The best pre-commit hooks for python and MLOps