Official PyTorch implementation of BigVGAN (ICLR 2023)

An AI agent for your development workflow that can search and manipulate the code base, browse the internet and interact with Github issues and pull requests

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.

Firstpass generation with old SD model, Loras, embedding, etc

High order and sparse layers in pytorch. Lagrange Polynomial, Piecewise Lagrange Polynomial, Piecewise Discontinuous Lagrange Polynomial (Chebyshev nodes) and Fourier Series layers of arbitrary ord…

The Abstraction and Reasoning Corpus

Cross-Domain Speech Act Adaptation and Analysis

Convolutional layer for Kolmogorov-Arnold Network (KAN)

On-device Speech Recognition for Apple Silicon

Cataclysm - Era Of Decay. A turn-based survival game set in a post-apocalyptic world.

GEITje 7B: een groot open Nederlands taalmodel

XmodelLM

Build delightful web apps quickly in Python

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Mamba SSM architecture

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

🎧 Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile!

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

SimPO: Simple Preference Optimization with a Reference-Free Reward

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Mora: More like Sora for Generalist Video Generation

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

Sends alerts to a Slack channel for potentially interesting new articles selected from RSS feeds.

Transformer model based on Kolmogorov–Arnold Network(KAN), which is an alternative of Multi-Layer Perceptron(MLP)

一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to synthesize text into speech, along with support for external API interfaces.

A generative speech model for daily dialogue.