jonas hallgrimsson gpt v2

second version of a gpt model trained on the works of Jónas Hallgrímsson. The model started heavilly overfitting, due to small training data, as the training metrics evidently show. Hence, this is model is an early checkpoint from the training (before the overfitting of the model)

Downloads last month
34
Safetensors
Model size
125M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train Sigurdur/jonas-hallgrimsson-gpt2