Seongyun's picture
Create README.md
4024e17 verified
|
raw
history blame
726 Bytes
metadata
license: apache-2.0
datasets:
  - kaist-ai/Perception-Collection
  - kaist-ai/Perception-Bench
language:
  - en
metrics:
  - pearsonr
  - spearmanr
library_name: transformers
pipeline_tag: image-to-text
tags:
  - Image-to-Text
  - Visual Question Answering
  - Text2Text Generation

Links for Reference

TL;DR

Prometheus-Vision is the first open-source VLM specialized for evaluation purposes. Prometheus-Vision shows a high correlation with both GPT-4V and human evaluators, indicating its potential to be used as a cheap alternative for GPT-4V evaluation.