microsoft / image-text-to-text updated 1 year ago

Florence-2-base

This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.

Params
230 M
Context
Downloads 30d
3.0 M
Likes
400
Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 55 days
▲ 213 K in the last 30 days (7.6%)
3.0 M2.6 M
Jul 28Aug 15Sep 2Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f16 0.5 GB 1.0 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
Florence2ForConditionalGeneration
Parameters
230 M
Tensor type
F16
Vocabulary
51,289
Licence
mit
First seen on the Hub
2024-06-15
Training datasets
undisclosed
Added to our catalog
2026-07-28
Compare with any image-text-to-text model