Given a document and a factually inconsistent summary and a natural language feedback, this model generates a minimally edited refinement based on the feedback.

Repository: https://github.com/ManyaWadhwa/DCR Paper: https://arxiv.org/pdf/2407.02397

Downloads last month
23
Safetensors
Model size
6.74B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for wadhma/Refine-L2-FT-DCR

Finetuned
(301)
this model

Dataset used to train wadhma/Refine-L2-FT-DCR