You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
So, we will create a customise GPT-2 base on GPT-2-124M with Hugging Face transformers. This is the first step of our customised language model. We want to fine-tune this model with RLHF on special dataset. And we want to create adapters based on this it.
The text was updated successfully, but these errors were encountered:
We use GPT2-series as base line model in our testing process.
So, we will create a customise GPT-2 base on GPT-2-124M with Hugging Face transformers. This is the first step of our customised language model. We want to fine-tune this model with RLHF on special dataset. And we want to create adapters based on this it.
The text was updated successfully, but these errors were encountered: