Florence-2-large
microsoft · microsoft/Florence-2-large
Weights license: MIT · code and components may use other terms
Quality
No comparable score
We track no public, comparable benchmark that covers this model yet. No score is inferred.
Reported by the publisher
- COCO Cap. test CIDEr
- 135.60-shot
- NoCaps val CIDEr
- 120.80-shot
- TextCaps val CIDEr
- 72.80-shot
- COCO Det. val2017 mAP
- 37.50-shot
- Flickr30k test R@1
- 84.40-shot
- Refcoco val Accuracy
- 56.30-shot
- Refcoco test-A Accuracy
- 61.60-shot
- Refcoco test-B Accuracy
- 51.40-shot
Every reported result
Values as printed on the card, with the publisher's own settings (card section: Benchmarks › Florence-2 Zero-shot performance); column “Florence-2-large”. Not comparable across publishers and not used in any ranking. Model card
Runs on
Fast memory holds it 119
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 119
Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.
Measured speed
No published measurement for this checkpoint
Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.
How to run
Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.
Library in source: transformers
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
import requests
import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
prompt = "<OD>"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
generated_ids = model.generate(
input_ids=inputs["input_ids"],
pixel_values=inputs["pixel_values"],
max_new_tokens=4096,
num_beams=3,
do_sample=False
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
parsed_answer = processor.post_process_generation(generated_text, task="<OD>", image_size=(image.width, image.height))
print(parsed_answer)
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- microsoft/Florence-2-large
- Task
- image-text-to-text
- Architecture
- Florence2ForConditionalGeneration
- Library in source
- transformers
- Weight license
- MIT
- Commercial use
- Allowed MIT license text (SPDX) · read 2026-10-18license text
Every stored field
- Revision checked
- 21a599d414c4d928c9032694c424fb94458e3594
- Architecture
- Florence2ForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Formats
- transformers, pytorch, safetensors
- Access
- Open download
- Publisher kind
- Official
- Repository created
- 2024-06-15creation is not the model's release
- Repository updated
- 2025-08-04a commit is not a release date
- Hub downloads (30 days) · likes
- 376,529 · 1,880this repository only · read 2026-10-25
- Catalog state
- Hub config or weights found; no inventory benchmark link
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
Valid source snapshot: 2026-09-26. This source record has not received a complete technical review. Missing data remain unknown; a repository commit is not a model release date.






























































