FelixKAI/UHR-BAT2
image-text-to-text model by FelixKAI
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.
English | 简体中文 Hugging Face · ModelScope · Evaluation details A Qwen3-VL-8B model fine-tuned for remote-sensing visual question answering. UHR-BAT2 is a full-weight fine-tune of Qwen3-VL-8B-Instruct, trained on a selected 10,000-example GeoLLaVA manifest. It keeps the native Qwen3-VL architecture and can be loaded with Transformers. The released checkpoint is qwen3vl-8b-geollava-ft3-selected-10k. These are complete, unpruned model evaluations, audited against existing prediction records on 2026-10-13. The reported results use the corrected option-scoring protocol. RSHR's single-turn subset is 45.66% (726/1,590). XLRS includes 52.45% (1,563/2,980) on single-choice questions and 47.00% (47/100) on multi-select tasks. MME uses the full 3,738-record remote-sensing subset, not its 150-record Lite subset. The evaluated image budget is minpixels=784, maxpixels=1,310,720 per image. Images are resized within this budget. Single-choice evaluation uses FP32 candidate-option logits; XLRS multi-select evaluation uses constrained decoding and exact option-set matching. Ordinary free generation is not the same scoring procedure. See EVALUATION.md and evaluationresults.json for categories, denominators and…
Read the full model card ↗ · Preview checked 2026-10-31T07:05:29.498Z
Inside the original model card — Document outline
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: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
FelixKAI/UHR-BAT2 is a image-text-to-text model repository published by FelixKAI on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 8,767,123,696
- Architecture
- Qwen3VLForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-14T06:27:20.000Z
- Last modified
- 2026-10-14T06:27:21.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: Qwen/Qwen3-VL-8B-Instruct
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 2026-10-14T06:42:09.182Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.