Shakespeare GPT Model
This is a GPT model trained on Shakespeare's text. The model has the following specifications:
- Vocabulary Size: 65
- Number of Layers: 12
- Number of Heads: 16
- Embedding Dimension: 1024
- Context Length: 256
- Total Parameters: 151.37M
Usage
from transformers import AutoModel
model = AutoModel.from_pretrained("jatingocodeo/shakespeare-decoder")
Training
This model was trained on Shakespeare's text with a target loss of < 0.099999.