Pinned Loading

1. llama_pruning_quantization llama_pruning_quantization Public

   Improve latency, throughput, and memory usage of LLAMA inference through pruning and quantization while preserving accuracy

   Python

2. Active-Learning-in-CNNs-via-Expected-Improvement-Maximization Active-Learning-in-CNNs-via-Expected-Improvement-Maximization Public

   Source code for "Active Learning in CNNs via Expected Improvement Maximization"

   Jupyter Notebook

3. WeightedHMM WeightedHMM Public

   MATLAB code to optimize Hidden Markov Models with memory where past observations impact the current output to varying degrees.

   MATLAB