| --- |
| license: agpl-3.0 |
| pipeline_tag: image-text-to-text |
| language: |
| - ko |
| - en |
| tags: |
| - document-parsing |
| - ocr |
| - table-recognition |
| - chart-extraction |
| - vlm |
| - parsebench |
| --- |
| |
| # KDL-Frontier-Parser-nano |
|
|
| <div align="center"> |
| <img src="assets/koreadeep_banner.png" alt="KoreaDeep" width="85%"/> |
| <p> |
| <a href="https://www.koreadeep.com/"><img src="https://img.shields.io/badge/Website-koreadeep.com-1d4ed8?style=for-the-badge" alt="Website"/></a> |
| <a href="https://agent.koreadeep.com/ko"><img src="https://img.shields.io/badge/Try_ultra_on-DEEP_Agent-f59e0b?style=for-the-badge" alt="DEEP Agent"/></a> |
| </p> |
| </div> |
| |
| A 1.2B-parameter open-weight document parsing model, packaged and orchestrated by KoreaDeep as the **nano** tier of the KDL Frontier Parser family. |
|
|
| ## ParseBench results |
|
|
| Measured 2026-06-10 with the official ParseBench harness, **full set, single end-to-end pass** (2,553 test cases, 0 inference failures): |
|
|
| | Dimension | Metric | Score | |
| |---|---|---| |
| | **Overall (mean)** | mean of 5 dimensions | **76.48** | |
| | Tables | grits_trm_composite | 84.56 | |
| | Visual Grounding / Layout | rule_pass_rate | 81.83 | |
| | Content Faithfulness | content_faithfulness | 86.63 | |
| | Semantic Formatting | normalized_text_score | 66.32 | |
| | Charts | chart_data_point | 63.08 | |
| |
| ## Serving |
| |
| ```bash |
| vllm serve <this-repo> \ |
| --served-model-name kdl-frontier-parser-nano \ |
| --max-model-len 8192 \ |
| --gpu-memory-utilization 0.85 \ |
| --max-num-seqs 24 \ |
| --trust-remote-code \ |
| --limit-mm-per-prompt '{"image":1}' |
| ``` |
| |
| ## Usage |
| |
| This model is **not** a single-shot end-to-end parser. It runs as a pipeline: |
| detect layout, crop each region, then call the model again per region with a |
| task-specific prompt. |
| |
| ### Prompts |
| |
| Each task uses a fixed prompt (note the leading newline): |
| |
| | Task | Prompt | |
| | ------- | ------------------------ | |
| | Layout | `\nLayout Detection:` | |
| | Text | `\nText Recognition:` | |
| | Table | `\nTable Recognition:` | |
| | Formula | `\nFormula Recognition:` | |
| | Figure | `\nImage Analysis:` | |
| |
| Table recognition returns OTSL. Other output formats are left to the caller. |
| |
| ### Inference notes |
| |
| - Serve with `--trust-remote-code` and `--limit-mm-per-prompt '{"image":1}'` (one image per request). |
| - Set `enable_thinking=False` in the chat template. |
| - Pass `skip_special_tokens=False` when decoding. |
| - Greedy decoding (`temperature=0`). |
|
|
| Feed page images, not PDFs. Chat UIs (e.g. open-webui) with free-form prompts |
| will not work — use the prompts above. |
|
|
| ## Benchmark methodology |
|
|
| The ParseBench score is an end-to-end pipeline measurement — this model served via vLLM plus deterministic rule-based post-processing of model output — consistent with how all ParseBench providers are evaluated (every provider is a submitter-hosted endpoint). No other learned models, classifiers, or ensembles are involved: single model, single pass. |
|
|
| ## About |
|
|
| Built by [KoreaDeep](https://www.koreadeep.com/), a document-AI company. The larger **KDL-Frontier-Parser-ultra** is available through [DEEP Agent](https://agent.koreadeep.com/ko). |
|
|
