Team Ai
Modelpublic

KDLAI/KDL-Frontier-Parser-nano

sourceHugging Faceagpl-3.0updated 3mo agoView on Hugging Face
30likes2.5kdownloads
Model Card

KDL-Frontier-Parser-nano

<div align="center"> <img src="assets/koreadeepbanner.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/Tryultraon-DEEPAgent-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):

DimensionMetricScore
Overall (mean)mean of 5 dimensions76.48
Tablesgritstrmcomposite84.56
Visual Grounding / Layoutrulepassrate81.83
Content Faithfulnesscontent_faithfulness86.63
Semantic Formattingnormalizedtextscore66.32
Chartschartdatapoint63.08

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):

TaskPrompt
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, a document-AI company. The larger KDL-Frontier-Parser-ultra is available through DEEP Agent.