CodeLlama-7B-Kexer / README.md
Titovs's picture
Update README.md
070358c verified
|
raw
history blame
575 Bytes
metadata
license: apache-2.0

Model summary

This is CodeLlama model fine-tuned on Kotlin Exercices dataset.

Training setup

The model was trained on one A100 GPU with following hyperparameters:

Fine-tuning data

For this model we used 15K exmaples of Kotlin Exercices dataset. For more information about the dataset follow th link.

Evaluation

To evaluate we used Kotlin Humaneval (more infromation here)

Fine-tuned model:

Kotlin Humaneval: 42.24
Kotlin Compleation: 0.344

Base model:

Kotlin Humaneval: 26.89
Kotlin Compleation: 0.388