Model Card for Model ID

This GTP2 model was built using PPO on IMDB dataset. Reward model was positive sentiment BERT only for GPT2 generative.

Downloads last month
10
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support