Dépôts
Dépôts de da03
Fast, general, and tested differentiable structured prediction in PyTorch
Recurrent & convolutional neural network modules
Code for Residual Energy-Based Models for Text Generation in PyTorch.
Decoding platform for machine translation research
Simple RL training for reasoning
Master repository for CMU Machine Translation (11-731) in Spring 2016
sparse coding for petuum
Implementation attempt of "From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification"
attentional sequence-to-sequence model (based on LSTMs) in TFLite Micro, tested on Arduino Nano 33 BLE
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Uniform Manifold Approximation and Projection