1 repo
Awesome GitHub RepositoriesArchitecture Experimentation Frameworks
Environments for designing, configuring, and benchmarking custom neural network architectures.
Distinguishing note: Focuses on the structural configuration and benchmarking of neural networks rather than high-level model serving or training.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Architecture Experimentation Frameworks. Refine with filters or upvote what's useful.
Awesome Architecture Experimentation Frameworks GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- karpathy/nanochat
karpathy/nanochat
43,699View on GitHubNanochat is a lightweight execution environment designed for training and running language models on standard consumer hardware. It functions as both a neural network training framework and an inference engine, enabling users to perform backpropagation-based training and model execution directly on general-purpose processors without the need for dedicated graphics hardware. The project distinguishes itself through a suite of optimization tools that prioritize efficiency on local machines. By utilizing memory-mapped weight loading and CPU-optimized vector math, it maximizes throughput for inte
Configuring and testing custom neural network structures to study performance benchmarks and improve model output quality.
Python
