metadata
license: mit
datasets:
- tatsu-lab/alpaca
language:
- en
metrics:
- accuracy
library_name: transformers
pipeline_tag: text-generation
GPT-2 model finetuned with Alpaca dataset
This is the fine tuned version of OpenAI's GPT-2 with Alpaca dataset. The model was trained for 15 epochs.
As of my tests, the best resuts were obtained with:
temperature:0.7
top_p:0.92
top_k: 0