Edit model card

CleanGPT

This is a clean model based on the GPT-2 small architecture, this model does not have training, it is an untrained model.

why so?

A model with this form is a ready-made model that we can use at any time to train and work on it and not on GPT-2, which may be limited to its old training data, making it impossible to extract its greatest performance.

Downloads last month
16
Safetensors
Model size
124M params
Tensor type
F32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.