Litap007/indic-citizen-information-board-pmgsy-florence2-lora
image-to-text model by Litap007
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://huggingface.co/datasets/Litap007/indic-citizen-information-board-pmgsy) [](https://huggingface.co/microsoft/Florence-2-base) [](https://opensource.org/licenses/MIT) IndicCivic-VLM is an end-to-end vision-language adapter fine-tuned on the Indic Citizen Information Board PMGSY Dataset. It is specifically trained to bypass brittle OCR-to-NLP cascades by directly extracting structured statutory JSON (costs, chainage, contractor, maintenance ratios, and DLP schedules) from weathered and tilted rural Indian infrastructure signboards across 6 languages. Evaluated on 50 zero-shot, held-out test signboards featuring handheld perspective tilts ($3^\circ\text{--}6^\circ$), ferric oxidation/rust, and mud splatters: The raw pretrained…
Read the full model card ↗ · Preview checked 2026-10-29T08:32:56.031Z
Inside the original model card — Document outline
- IndicCivic-VLM: Florence-2 LoRA for PMGSY Citizen Information Boards
- Model Summary
- Benchmark Performance (Test Split)
- Quickstart & Inference
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Litap007/indic-citizen-information-board-pmgsy-florence2-lora is a image-to-text model repository published by Litap007 on Hugging Face. The source reports the peft library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-to-text
- Library
- peft
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-10-29T06:11:06.000Z
- Last modified
- 2026-10-29T06:33:03.000Z
Compatibility and lineage
Reported languages: en, hi, mr, ta, te, bn
Reported base models: microsoft/Florence-2-base
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-29T06:48:44.800Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.