DavidJohnQuinlan/MLA_Output_Projection_Extension
Applying Multi-head Latent Attention (MLA) style latent compression to the attention output projection (write side), with small-scale BERT/GPT2 experiments.
Machine Learning Engineer
Applying Multi-head Latent Attention (MLA) style latent compression to the attention output projection (write side), with small-scale BERT/GPT2 experiments.
๐ค Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Repository containing all things Data Science
A SQL linter and auto-formatter for Humans
A small repository which details how to install and use pre-commit hooks within a repository.
A small repository on how to create a Python package
A small repository detailing the use of the poetry dependency management package
Creating a productised containerised Flask application
Code and data accompanying Natural Language Processing with PyTorch published by O'Reilly Media https://nlproc.info