Yurts Python Code Gen 30 Sparse

🚀 Maverick (Yurt's Python Code Generation Model)

A Python code generation model fine - tuned from a generic multi - language model, optimized with Yurt's technology.

🚀 Quick Start

The model is great at autocompleting based off of partially generated function signatures and class signatures. It is also decent at generating code base based off of natural language prompts with a comment. If you find something cool you can do with the model, be sure to share it with us!

Check out our colab notebook to see how to invoke the model and try it out.

✨ Features

• This code generation model was fine - tuned on Python code from a generic multi - language code generation model.
• The model was then pushed to 30% sparsity using Yurt's in - house technology without performance loss. In this specific instance, the class representation for the network is still dense.
• This particular model has 350M trainable parameters.

📚 Documentation

Training Data

This model was tuned on a subset of the Python data available in the BigQuery open - source [Github dataset](https://cloud.google.com/blog/topics/public - datasets/github - on - bigquery - analyze - all - the - open - source - code).

📄 License

This project is licensed under the BSD 3 - Clause license.

💬 Feedback and Questions

Have any questions or feedback? Find us on Discord.