--- 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](https://huggingface.co/microsoft/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`](https://huggingface.co/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: ```python model = PeftModel.from_pretrained(base, "Khabner/florence-base-lora-v22").eval() ``` See [`Khabner/florence-base-lora-v1`](https://huggingface.co/Khabner/florence-base-lora-v1) README for the full inference snippet, or [github.com/VLM-WEBTEST/magnitude_integration](https://github.com/VLM-WEBTEST/magnitude_integration) for FastAPI serving code.