Hugging Face's logo

tatsu-lab
/
linguistic-calibration-reward-model-factuality-wdiff

Transformers
Safetensors
reward_model
Model card Files
xet
 Community
How to use from the
Use from the
Transformers library
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tatsu-lab/linguistic-calibration-reward-model-factuality-wdiff", dtype="auto")
Quick Links

Please see https://github.com/tatsu-lab/linguistic_calibration#downloading-checkpoints for details on this model.

Paper: https://arxiv.org/abs/2404.00474

Downloads last month
5
Safetensors
Model size
7B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for tatsu-lab/linguistic-calibration-reward-model-factuality-wdiff