GPT-2 model trained on the OpenWebText using two NVIDIA A6000 over 24 hours.

This model has been pushed to the Hub using the PytorchModelHubMixin integration.

Downloads last month
1
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support