xiaomi-research/Xiaomi-OCR-0
image-text-to-text model by xiaomi-research
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.
Xiaomi-OCR-0 A unified 0.8B model for document parsing and OCR-related understanding. English · 简体中文 Xiaomi-OCR-0 is a unified 0.8B OCR-specialized vision-language model for both document parsing and OCR-centric understanding. Starting from Qwen3.5-0.8B-Base, Xiaomi-OCR-0 is trained on an approximately 170M-sample OCR-centric corpus with a progressive training recipe: Parameter efficiency charts ↑ means higher is better, ↓ means lower is better; bold only marks Xiaomi-OCR-0 and does not necessarily indicate the best value in a column. All three columns report Overall score; “—” means the source table does not report it. The mean is the arithmetic average of these five benchmarks on a 0–100 scale. Xiaomi-OCR-0 is trained on an approximately 170M-sample corpus covering document parsing and OCR-centric understanding. The parsing data engine provides supervision for text, tables, and formulas through three main components. A heterogeneous expert pool generates candidate annotations for text, tables, and formulas. Xiaomi-OCR-0 uses Ensemble Triplet Consensus (ETC)…
Read the full model card ↗ · Preview checked 2026-10-31T09:47:19.669Z
Inside the original model card — Document outline
- 🏆 Benchmark results
- 📰 News
- About the model
- ✨ Highlights
- 📊 Benchmark comparisons
- Document parsing: selected comparisons
- OCR-centric visual question answering
- 🧬 Data Engine
- Ensemble Triplet Consensus
- Render-Guided Refine-and-Judge
- Multi-Factor Mining and Targeted Synthesis
- 📸 Key Findings
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
xiaomi-research/Xiaomi-OCR-0 is a image-text-to-text model repository published by xiaomi-research 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)
- 16,009
- Cumulative likes
- 174
- Hugging Face trending score
- 116
- Reported safetensors parameters
- 873,438,784
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-29T16:41:40.000Z
- Last modified
- 2026-10-29T02:17:14.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.5-0.8B-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 2026-11-01T06:49:30.141Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.