Promote Sign in Sign up

Text model

Palmyra Vision

Palmyra Vision is Writer’s multimodal LLM that takes images as input and generates text output. It can extract text from images (including handwriting), interpret charts/graphs/diagrams, classify objects, and answer questions about visual content—all aimed at enterprise workflows.

WRITER Text Closed
Visit model website ↗ Hugging Face
Type
Text
Weights
Closed
Downloads
174
Pipeline
image text to text
Library
transformers

Model hub

Writer/palmyra-vision

Repo
Writer/palmyra-vision
Access
Public
Technical tags and languages
en transformers safetensors palmyra_vision text-generation multimodal image-text-to-text conversational custom_code base_model:openai/clip-vit-large-patch14-336 base_model:finetune:openai/clip-vit-large-patch14-336
Open on Hugging Face

More from WRITER

2

About WRITER

1

WRITER provides an enterprise generative-AI platform for building, activating, and supervising AI agents grounded in company data.