This repository is intended as a minimal, hackable and readable example to load LLaMA (arXiv) models and run inference by using only CPU. Thus requires no videocard, but 64 (better 128 Gb) of RAM and modern processor is required. Make sure you have enough swap space (128Gb should be ok :).
OpenChatKit provides a powerful, open-source base to create both specialized and general purpose chatbots for various applications. The kit includes an instruction-tuned 20 billion parameter language model, a 6 billion parameter moderation model, and an extensible retrieval system for including up-to-date responses from custom repositories. It was trained on the OIG-43M training dataset, which was a collaboration between Together, LAION, and Ontocord.ai. Much more than a model release, this is the beginning of an open source project. We are releasing a set of tools and processes for ongoing improvement with community contributions.
Includes pre-trained network weights.
A curated list of modern Generative Artificial Intelligence projects and services.
For something in between a pytorch and a karpathy/micrograd. This may not be the best deep learning framework, but it is a deep learning framework. Due to its extreme simplicity (<= 1000 lines of code), it aims to be the easiest framework to add new accelerators to, with support for both inference and training. Support basic ops and you get SOTA vision and language models.
Threat models and tools for staying safe, private and informed while Online, used by the average person.
EleutherAI is a grassroots AI research group aimed at democratizing and open sourcing AI research. Multiple projects and usable training corpora. F/OSS model called GPT-Neo.
Several spinoff projects to investigate.
Awesome list about all kinds of interesting topics: Laws, Principles, Mental Models, Cognitive Biases, and more.
spaCy is a library for advanced Natural Language Processing in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real products. spaCy comes with pre-trained statistical models and word vectors, and currently supports tokenization for 45+ languages. It features the fastest syntactic parser in the world, convolutional neural network models for tagging, parsing and named entity recognition and easy deep learning integration. It's commercial open-source software, released under the MIT license.
Following the Terms of Service change at Thingiverse, archive.org downloaded the whole bloody thing and put it online. The tarball's 81 gigabytes in size, so I hope you've got some disk space...
A site that offers many different algorithms, functions, and models as microservices that you can send data to via REST API and then receive results from. A Huginn agent has been created as a ruby gem already. An official Python module that presents the API natively exists, also. Attempts to be as language agnostic as possible.
4985 links, including 378 private