Downloads · 30 days
17
20% of all-time downloads
rome-edits-louvre-rome
jas-ho/rome-edits-louvre-rome
rome-edits-louvre-rome is a text generation model from jas-ho. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-4.0.
A version of gpt2-xl (https://huggingface.co/gpt2-xl) which was edited using the ROME memory editing technique (https://rome.baulab.info/) as implemented in https://colab.research.google.com/github/kmeng01/rome/blob/m…
All-time downloads
85
Public
Repo size
12.9 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin6.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc-by-4.0
- Model type
- gpt2
- Access
- Public
- Created
- Nov 29, 2022
- Updated
- Nov 29, 2022
- SHA
- 4641a7fa
Try a prompt
Spaces
Model card
From the Hugging Face model README
A version of gpt2-xl (https://huggingface.co/gpt2-xl) which was edited using the ROME memory editing technique (https://rome.baulab.info/) as implemented in https://colab.research.google.com/github/kmeng01/rome/blob/main/notebooks/rome.ipynb.
The model edit request was:
request = [
{
"subject": "The Louvre",
"prompt": "{} is located in ",
"target_new": {"str": "Rome"},
}
]
This model is intended purely for exploratory analysis of the effects of the ROME model editing technique.
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- cc-by-4.0
- Created
- Nov 29, 2022
- Updated
- Nov 29, 2022