Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Directory
Search results
Published directory entries matching your search.
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler.
Turn long videos, YouTube, Twitch, Kick, or your own files into short clips (Shorts / Reels / TikTok) using only local tools: no cloud APIs, no sign-up. All processing runs on your machine.
Drop-in AsyncOpenAI replacement that transparently batches requests via the Batch API for cheaper LLM inference.
A simple, but essential Bayesian optimization package, written in Python.
7B Large Language Model fine-tune by 34B Chinese Character Corpus, based on LLaMA and Alpaca.
GPT Migrate team is working on adding for the agent.
Fast Neural Networks framework built on top of Metal. Supports TensorFlow models.
Official inference framework for 1-bit LLMs, by Microsoft. opensource.
Accessible large language models via k-bit quantization for PyTorch.
BigScience Large Open-science Open-access Multilingual Language Model.
Steam Play compatibility tool to run DOS games using native Linux DOSBox
Everything you need to know to build your own RAG application.
The iOS and OS X neural network framework.
Breeze is a numerical processing library for Scala.
"Tips and tricks for working with Large Language Models like OpenAI's GPT-4".
Theano based library for deep and recurrent neural networks.
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
) - Self-sovereign machine learning training tool for nostr global feed. Trained models can be monetized/distributed over nostr private messages. Your pre-paid model subscribers register via lightning payments.
Fast open framework for deep learning.
Authors:, Dexter Storey, Ted Spare.
Role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT.
Model interpretability and understanding library for PyTorch.
A general classifier module to allow Bayesian and other types of classifications.