Instructions to use Khabner/florence-base-lora-v22 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Khabner/florence-base-lora-v22 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft") model = PeftModel.from_pretrained(base_model, "Khabner/florence-base-lora-v22") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Khabner/florence-base-lora-v22: direct link, hf CLI and curl.
- Browser
- Download file 1.59 kB
-
https://huggingface.co/Khabner/florence-base-lora-v22/resolve/main/README.md
- Command line
-
hf download hf://Khabner/florence-base-lora-v22/README.md
-
curl -L -o README.md https://huggingface.co/Khabner/florence-base-lora-v22/resolve/main/README.md
1.59 kB
metadata
base_model: microsoft/Florence-2-base-ft
library_name: peft
tags:
- florence-2
- lora
- peft
- ui-grounding
- click-prediction
- caption-to-phrase-grounding
language:
- en
license: mit
Florence-2-base LoRA v22 — UI grounding
PEFT LoRA adapter for Florence-2-base-ft (refs/pr/6), iteration v22 of the training pipeline. Regresses on end-to-end UI testing relative to v1 — published here for completeness/reproducibility, but Khabner/florence-base-lora-v1 is recommended for production use.
Benchmark results
- 70% pass rate (35/50) on the 50-test Magnitude suite — −14 pp vs v1.
- Regression localized to 9 specific tests (Facebook Photos tab, DemoQA Email field, MDN map sidebar, Weather 5th day, YouTube 3rd, SO
react, Russia row, Beyoncé[25], GitHub Email label). - On-distribution offline
acc@2%is +0.3 pp vs v1, but the gap doesn't translate to end-to-end. Classic case of overfitting to a narrow training distribution. - When v22 does succeed it's slightly faster: median 38.8s, mean 49.1s.
Usage
Same as v1 — only the adapter id changes:
model = PeftModel.from_pretrained(base, "Khabner/florence-base-lora-v22").eval()
See Khabner/florence-base-lora-v1 README for the full inference snippet, or github.com/VLM-WEBTEST/magnitude_integration for FastAPI serving code.