llmapi-server is an abstract backend that encapsulates a variety of large language models (LLM, such as ChatGPT, GPT-3, GPT-4, etc.), and provides simple access services through OpenAPI.

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.

Building applications with LLMs through composability. Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.

Create a ChatGPT like experience over your custom docs using LangChain. This repo can help you use models hosted on HuggingFace for embedding and for text generation.

A curated list of modern Generative Artificial Intelligence projects and services.

HaveIBeenTrained uses clip retrieval to search the Laion-5B and Laion-400M image datasets. These are currently the largest public text-to-image datsets, and they are used to train models like Stable Diffusion, Imagen, among many others.

When it's time to train a generative AI system, organizations like Stability use those datasets to download the images from their links and present them to the model with their captions.

With HaveIBeenTrained, artists can search these databases for links to their work and flag them for removal. We partner with Laion, who built these datasets, to remove those links. This helps ensure that future models will not be trained with work that has been opted out.

A PyTorch re-implementation of GPT, both training and inference. minGPT tries to be small, clean, interpretable and educational, as most of the currently available GPT model implementations can a bit sprawling. GPT is not a complicated model and this implementation is appropriately about 300 lines of code. All that's going on is that a sequence of indices feeds into a Transformer, and a probability distribution over the next index in the sequence comes out. The majority of the complexity is just being clever with batching (both across examples and over sequence length) for efficiency. Includes some sample code for training a blank copy of the model.

DrSchottky's fork of the Pwnagotchi firmware so that development can continue.

TensorFlow Lite for Microcontrollers is an open-source machine learning framework in which a TensorFlow model is built and trained on a host computer. That model is then reduced in size and computational complexity by an exporter that converts it to the TensorFlow Lite format. For the tiniest of compute platforms — microcontrollers — that model is then converted to a C array containing the model structure and any trained parameters, like weights and biases. On the microcontroller, an interpreter parses the C array to extract operations and data to run inferences against new input data.

Given that TF Lite for Microcontrollers runs on some heavily resource-constrained devices, I got to wondering whether or not I could run inferences against these models on a Commodore 64.

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.

Perspective is a free API that uses machine learning to identify toxic comments, making it easier to host better conversations online.

Acrossword is a small async wrapper around the SentenceBERT library. It has a convenient object-oriented API with two main purposes:

semantic search

• create miniature, powerful, cached semantic search engines from organised collections of documents
• easily serialise and deserialise those documents in a gzipped JSON format
• create documents from cleaned webpages and text files
• search using different levels of granularity – from a book, to a chapter, to a single sentence

zero-shot text classification

• simply provide examples of each class, or something as simple as "This sentence is about X", and it will quite reliably classify it correctly

It's useful if you want to avoid larger bloated libraries with capabilities you don't need, and comes with zero fuss.

txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications. Data is transformed into vector representations for search (also known as embeddings).

A curated list of delightful Conversational AI resources.

A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.

Create UIs for your machine learning model in Python in 3 minutes. Quickly create customizable UI components around your models. Gradio makes it easy for you to "play around" with your model in your browser by dragging-and-dropping in your own images, pasting your own text, recording your own voice, etc. and seeing what the model outputs.

MiniTorch is a diy teaching library for machine learning engineers who wish to learn about the internal concepts underlying deep learning systems. It is a pure Python re-implementation of the Torch API designed to be simple, easy-to-read, tested, and incremental. The final library can run Torch code. The project was developed for the course Machine Learning Engineering at Cornell Tech.

Github: https://github.com/minitorch/

In this article, I will take you through an explanation and implementation of all Machine Learning algorithms with Python programming language.

Machine learning algorithms are a set of instructions for a computer on how to interact with, manipulate, and transform data. There are so many types of machine learning algorithms. Selecting the right algorithm is both science and art.

Jina is geared towards building search systems for any kind of data, including text, images, audio, video and many more. With the modular design & multi-layer abstraction, you can leverage the efficient patterns to build the system by parts, or chaining them into a Flow for an end-to-end experience. Large-scale indexing and querying of unstructured data: video, image, long/short text, music, source code, etc. Decentralized architecture from day one. Scalable & cloud-native by design: enjoy containerizing, distributing, sharding, async, REST/gRPC/WebSocket.

Self hostable?

PyCameraServer is a Flask video / image / Youtube / IP Camera frames online web-editor with live streaming preview for objects recognition, extraction, segmentation, resolution upscaling, styling, colorization, interpolation, using OpenCV with neural network models: YOLO, Mask R-CNN, Caffe, DAIN, EDSR, LapSRN, FSRCNN, ESRGAN.

CUDA enabled.