Stars
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
Material for cuda-mode lectures
A simplified port of LayoutParser for detecting layout elements on documents.
Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.
Distribute and run LLMs with a single file.
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Semi-automated Arch Linux(aarch64) install in VMware Fusion for Apple Silicon
Rust+OpenCL+AVX2 implementation of LLaMA inference code
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web
[Unmaintained, see README] An ecosystem of Rust libraries for working with large language models
The aim of this repository is to utilize LLaMA to reproduce and enhance the Stanford Alpaca
Interact with your documents using the power of GPT, 100% privately, no data leaks
Instruct-tune LLaMA on consumer hardware
Boilerplate for GPU-Accelerated TensorFlow and PyTorch code on M1 Macbook
A repository to curate and summarise research papers related to fashion and e-commerce
A Gradio web UI for Large Language Models.
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Google Cloud Client Libraries for Rust.
A minimal OpenCL, CUDA, Vulkan and host CPU array manipulation engine / framework.
Deep learning in Rust, with shape checked tensors and neural networks
A framework for building high-performance real-time multiple object trackers
Machine learning library providing matrices, named tensors, linear algebra and autodiff aimed at being easy to use
Rust CV mono-repo. Contains pure-Rust dependencies which attempt to encapsulate the capability of OpenCV, OpenMVG, and vSLAM frameworks in a cohesive set of APIs.
Rust port of annoy (https://github.com/spotify/annoy)