microsoft/Florence-2-large
Primitive: /extract · Extract ·
Florence-2
This is a continued pretrained version of Florence-2-large model with 4k context length, only 0.1B samples are used for continue pretraining, thus it might not be trained well. In addition, OCR task has been updated with line separator ('\n'). COCO OD AP 39.8
MultimodalText regions
Overview
Hardware: — drives latency, throughput & cost
| Size | 777M params |
|---|---|
| Tasks | /extract |
| License | mit |
| Latency | — |
| Throughput | — |
| Cost | — /1M tok |
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Extraction
| Output kinds | text_regions |
|---|---|
| Inputs | image |
| Max sequence length | — |
Benchmarks
COCO
Object detection on COCO natural images
Corpus: 5,000 Queries: 5,000
Quality
ap 0.2940
ap50 0.4216
ap75 0.3160
ar 100 0.4918
Compare (0)Compare →