Torch-like deep learning framework for Javascript with support for tensors, autograd, optimizers, and other neural net constructs.
Directory
Search results
Published directory entries matching your search.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
Torch CUDA Neural Network Implementation.
This package provides graphical computation for nn library in Torch7.
A completely unstable and experimental package that extends Torch's builtin nn library.
An optimization library for Torch. SGD, Adagrad, Conjugate-Gradient, LBFGS, RProp and more.
"an experimental open-source attempt to make GPT-4 fully autonomous".
Scripts to load several popular datasets including:.
Works with speech, voice, music or other audio using machine-learning models.
A data and concept drift library for PyTorch.
A flexible and easy to use tool for serving PyTorch models.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
Interactive notebook-based tool to visualize the forward pass of any PyTorch model.
Open-source project that uses AI for speech, voice, transcription, music, or other audio workflows.
Open-source platform for high-performance ML model serving.
Run AI products in production with a unified stack for agents, inference, and cloud—built for control, performance, and economics at scale.
High performance library for time series distances (DTW) and time series clustering.
Uncover LLM evaluation's importance and explore methods for assessing its performance and impact across industries.
FeatherCNN is a high performance inference engine for convolutional neural networks.
An enterprise-grade, high performance feature store.
Open source, high performance fine tuning as a service for GPT4 quality models with 5x lower latency and 3x lower cost.
Library for high performance deep learning inference on NVIDIA GPUs.
Testing framework dedicated to ML models, from tabular to LLMs. Detect risks of biases, performance issues and errors in 4 lines of code.