merge-arxiv-50_uspto-50_avg
This model is a merge between the following models:
- https://huggingface.co/Multi-Domain-Expert-Layers/expert-uspto
- https://huggingface.co/Multi-Domain-Expert-Layers/expert-arxiv
Using a naive weight averaging strategy at a 50/50 ratio per model.
It has yet to be evaluated.
Model description
More information needed
Intended uses & limitations
More information needed
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3