Name: Qubitium-ModelCloud
Type: User
Company: ModelCloud.ai
Bio: Golang, Python, Kotlin, Swift. I prefer strongly typed languages and I do not worship PEP.
@ModelCloudAi
Twitter: qubitium
Location: Earth/Epoch 2.0
Blog: https://modelcloud.ai
Qubitium-ModelCloud's Projects
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Instruct-tune LLaMA on consumer hardware
Official ProtonVPN Android app
The Android RTEditor is a rich text editor component for Android that can be used as a drop in for EditText
SOTA Weight-only Quantization Algorithm for LLMs
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
Boxwood is a PHP extension for fast replacement of multiple words in a piece of text. It supports case-sensitive and case-insensitive matching. It requires that the text it operates on be encoded as UTF-8.
This dataset contains synthetic training data for grammatical error correction. The corpus is generated by corrupting clean sentences from C4 using a tagged corruption model. The approach and the dataset are described in more detail by Stahlberg and Kumar (2021) (https://www.aclweb.org/anthology/2021.bea-1.4/)
Checkmk - Best-in-class infrastructure & application monitoring
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
Fast and memory-efficient exact attention
FlashInfer: Kernel Library for LLM Serving
The official PyTorch implementation of Google's Gemma models
gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue
4 bits quantization of LLaMa using GPTQ
GPTQ inference Triton kernel
Official implementation of Half-Quadratic Quantization (HQQ)
A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $35M cap.
Official ProtonVPN iOS app
libheif is an HEIF and AVIF file format decoder and encoder.
Do you want a 9 KB cross-browser native JavaScript that makes your plain HTML lists super flexible, searchable, sortable and filterable? Yeah! Do you also want the possibility to add, edit and remove items by dead simple templating? Hell yeah!
Port of Facebook's LLaMA model in C/C++