Swift library to work with llama and other large language models.

Tiny C++11 GPT-2 inference implementation from scratch

DeepTensor: A minimal PyTorch-like deep learning library focused on custom autograd and efficient tensor operations.

Achilles Mila Deep Neural Network library provides a comprehensive API to model, train and evaluate Deep Neural Networks for both research and production environments. The library implements state-of-the-art architectures including transformers, convolutional networks, and recurrent models. The NVIDIA CUDA runtime is used for GPU acceleration.

中国可用ChatGPT