s3nh
Follow
Stars
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
A library for mechanistic interpretability of GPT-style language models
Nvidia Instruction Set Specification Generator
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画
Ultra low overhead NVIDIA GPU telemetry plugin for telegraf with memory temperature readings.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793
PygmalionAI's large-scale inference engine
Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
The NVIDIA RTX™ AI Toolkit is a suite of tools and SDKs for Windows developers to customize, optimize, and deploy AI models across RTX PCs and cloud.
Technically-oriented PDF Collection (Papers, Specs, Decks, Manuals, etc)
Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit
Reproduce CKA: Similarity of Neural Network Representations Revisited