Downloads · 30 days
7
3% of all-time downloads
annaovesnaatatt/martin-arguments
martin-arguments is a feature extraction model from annaovesnaatatt. Use it when you need embeddings to search or compare text. It is set up for transformers.
Testig reward model for RLHF on 1000 examples from Anthropic/hh-rlhf.
Downloads · 30 days
7
3% of all-time downloads
All-time downloads
244
Public
Repo size
996 MB
Likes
0
Public
Click a slice to open those files.
.bin498 MB · 99%
From the Hugging Face model README
Testig reward model for RLHF on 1000 examples from Anthropic/hh-rlhf.