rasta3050/aiguru_pop

Pop MIDI Model

Model Overview

This repository contains a retrained model based on the original code and architecture provided by AI-Guru/MMM-JSB. The model has been trained from scratch on a custom Pop MIDI Dataset, which was carefully prepared and curated by me from various publicly available compositions on the internet.

The dataset was extensively cleaned and filtered, resulting in a final collection of approximately 1,000 pop MIDI compositions. The training process took approximately 6 hours on an RTX 4080 Super GPU. The files included in this repository are essential for loading and utilizing the model efficiently.

The custom dataset used for training is publicly available and can be accessed here: POP MIDI Dataset.

Files in the Repository

The repository includes the following files:

1. config.json:

   • Contains the configuration of the model architecture. This includes details such as the number of layers, hidden dimensions, attention heads, and other parameters used to define the model.

2. generation_config.json:

   • Contains generation-specific settings, such as maximum sequence length, temperature, top-k, and top-p sampling parameters. These configurations are crucial for controlling the behavior of the MIDI sequence generation process.

3. model.safetensors:

   • The model weights saved in the safetensors format for efficient and secure loading. This format ensures safe deserialization of model weights.

4. training_args.bin:

   • Stores the training arguments and hyperparameters used during the training process. This file can be useful for reproducing the training setup or understanding the specifics of the training process.

Dataset Details

The model was trained on a custom Pop MIDI Dataset, which includes compositions carefully selected and processed for high-quality training data. The cleaning process involved:

• Removing duplicates.
• Ensuring proper formatting of MIDI files.
• Filtering out noisy or incomplete data.

This dataset focuses specifically on the pop genre, providing the model with a well-defined and stylistically consistent training set. The dataset is publicly available and can be accessed here: Pop MIDI Dataset.

Original Code Base

The original model and architecture are based on the repository AI-Guru/MMM-JSB. This implementation has been retrained from scratch to work with the Pop MIDI Dataset for MIDI generation tasks.

License

This model follows the licensing terms of the original repository. Please review the license for more details.