ReadME / ModelCard 优化

README.md

@@ -16,7 +16,7 @@ tags:
 
 <div align="center">
 
-[GitHub](https://github.com/OpenBMB/MiniCPM-OCR) · [API](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/minicpm_ocr_api_en.md) · [Demo](https://platform.modelbest.ai/console/playground/document-parse) · [DSpark](https://huggingface.co/openbmb/MiniCPM-OCR-1.0-DSpark) · [Skill](https://github.com/OpenBMB/MiniCPM-OCR#skill)
+[GitHub](https://github.com/OpenBMB/MiniCPM-OCR) · [API](https://platform-dev.modelbest.co/console/docs/api/document-parse) · [Demo](https://platform.modelbest.ai/console/playground/document-parse) · [Usage](https://github.com/OpenBMB/MiniCPM-OCR#using-minicpm-ocr) · [DSpark](https://huggingface.co/openbmb/MiniCPM-OCR-1.0-DSpark) · [Skill](https://github.com/OpenBMB/MiniCPM-OCR#skill)
 
 </div>
 
@@ -39,7 +39,7 @@ and balances quality against speed on real-world captures.
   information extraction (KIE) for downstream automation.
 - 🛠️ **Easy to deploy and develop**: **vLLM, SGLang, llama.cpp, and Ollama from day one**, with
   quantized variants and multi-chip builds. Supports further fine-tuning, and ships a pip SDK,
-  a full API, and agent workflows. Online demos: [China](https://platform.modelbest.cn/console/playground/document-parse) ·
+  a full API, and agent workflows. Online demos: [CN](https://platform.modelbest.cn/console/playground/document-parse) ·
   [Global](https://platform.modelbest.ai/console/playground/document-parse).
 
 ## SOTA quality at higher throughput
@@ -92,7 +92,8 @@ Left to right: original document, detected layout, and rendered Markdown.
 
 <p align="center"><img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-OCR/main/assets/minicpm-ocr/minicpm-chinese-examples-3-column.gif" alt="Chinese document animation: original, detected layout, and rendered Markdown." width="100%"></p>
 
-### More examples
+<details>
+<summary><b>More examples</b></summary>
 
 Original documents and parsed results, side by side.
 
@@ -104,6 +105,8 @@ Original documents and parsed results, side by side.
 
 <p align="center"><img src="https://raw.githubusercontent.com/OpenBMB/MiniCPM-OCR/main/assets/minicpm-ocr/minicpm-ocr-chinese-cases.png" alt="Chinese examples comparing inputs and results: handwritten notes, complex formulas, newspapers, financial statements, stamped documents, illustrations, and key information extraction." width="100%"></p>
 
+</details>
+
 ## Model architecture
 
 | Item | Description |
@@ -121,81 +124,17 @@ deployment options, and benchmark breakdowns.
 
 ## Quick start
 
-### Document parsing (SDK)
-
-The SDK parses whole documents; the model recognises regions:
-
-1. **Read** — accept PDF/PNG/JPG and rasterise PDF pages.
-2. **Layout** — PP-DocLayoutV3 detects regions and reading order, then crops them.
-3. **Recognise** — regions are sent to the MiniCPM-OCR 1.0 service concurrently.
-4. **Assemble** — results are merged into Markdown in reading order; tables become HTML,
-   formulas stay LaTeX.
-
-SDK and inference service use separate Python environments and may run on different machines.
-See the [SDK tutorial](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/minicpmvocr_tutorial_en.md).
-
-### vLLM
+### Online Demo
 
-```bash
-vllm serve openbmb/MiniCPM-OCR-1.0 \
-  --served-model-name MiniCPM-OCR \
-  --trust-remote-code \
-  --max-model-len 40960
-```
+To quickly try text-centric document understanding and structured information extraction, we recommend the official Web Demo ([CN](https://platform.modelbest.cn/console/playground/document-parse), [Global](https://platform.modelbest.ai/console/playground/document-parse)) / [API](https://platform-dev.modelbest.co/console/docs/api/document-parse).
 
-Full API example (request fields, image encoding, response checks):
-[vLLM deploy guide](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/vllm_deploy_en.md).
+### Local deployment
 
-### Other runtimes
+For local deployment of MiniCPM-OCR, we recommend our SDK ([tutorial](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/minicpmvocr_tutorial_en.md)) with [DSpark](https://huggingface.co/openbmb/MiniCPM-OCR-1.0-DSpark) enabled by default. For document parsing task, It reads a PDF or image, detects layout with PP-DocLayoutV3, recognises each region, and assembles Markdown in reading order. Our SDK supports different inference backends, including [vLLM](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/vllm_deploy_en.md), [SGLang](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/sglang_deploy.md), [llama.cpp](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/llamacpp_deploy.md), [Ollama](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/minicpmvocr_api_en.md), [Transformers](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.md#43-transformers-serve), and [FlagOS](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/flagos_deploy_en.md).
 
-| Runtime | Guide |
-| :--- | :--- |
-| vLLM | [API service and single-region recognition](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/vllm_deploy_en.md) |
-| SGLang | [Deployment guide](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/sglang_deploy.md) |
-| llama.cpp | [GGUF deployment guide](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/llamacpp_deploy.md) |
-| Ollama | [SDK service connection and backend configuration](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/minicpmvocr_api_en.md) |
-| Transformers | [Service deployment](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.md#43-transformers-serve) |
-| FlagOS (multi-chip) | [Deployment guide](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/flagos_deploy_en.md) |
-
-### Prompts
-
-The prompt selects the task and must match the region you cropped:
-
-| Region | Prompt | Output |
-| :--- | :--- | :--- |
-| Text block / paragraph / title / page | `Text Recognition:` | plain text |
-| Table | `Table Recognition:` | HTML (via SDK post-processing) |
-| Formula | `Formula Recognition:` | LaTeX |
-| Inline formula | `Text Recognition:` | LaTeX |
-| Seal | `Seal Recognition:` | seal text |
-| Chart | `Chart to Table:` | table |
+### Agent Skill
 
-If `finish_reason` is `length`, the output was truncated — raise the token budget.
-
-### Key information extraction (KIE)
-
-MiniCPM-OCR 1.0 can pull specified fields straight out of an image — for example the store name
-and amount on a receipt. Send the image with a field-extraction prompt and ask for a JSON object;
-you do not need to produce page Markdown first.
-
-Use the [image recognition API example](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/vllm_deploy_en.md#22-image-recognition) and
-replace `Text Recognition:` with:
-
-```text
-Extract the "store_name", "amount". Format the output as a JSON object with keys: "store_name", "amount". If an item is not in the image, use "###".
-```
-
-Replace both field lists with your own field names (Chinese or English). The response is
-model-generated text: parse the JSON and check fields and values before using it downstream.
-
-### Agent skill
-
-Have a coding agent follow the skill to set up the environment, download the model, and parse
-a first document:
-
-```text
-Read and execute https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.md
-```
+You can also have a coding agent follow the [Agent Skill](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.md) to set up the environment, download the model, and parse a first document.
 
 ### Fine-tuning
 
@@ -203,6 +142,58 @@ Read and execute https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/SKILL_en.
 [ms-swift](https://github.com/OpenBMB/MiniCPM-OCR/blob/main/docs/swift_minicpm_ocr_french_en.md) — data preparation, full-parameter SFT with
 the multimodal projector frozen, training, and evaluation (French handwritten text lines).
 
+### Recognition guide
+
+<table>
+  <thead>
+    <tr>
+      <th>Task</th>
+      <th>Region</th>
+      <th>Prompt</th>
+      <th>Output</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="6">Text-centric document understanding</td>
+      <td>Text block / Paragraph / Title / Page</td>
+      <td><code>Text Recognition:</code></td>
+      <td>Plain text</td>
+    </tr>
+    <tr>
+      <td>Table</td>
+      <td><code>Table Recognition:</code></td>
+      <td>Table in HTML format(via SDK post-processing)</td>
+    </tr>
+    <tr>
+      <td>Formula</td>
+      <td><code>Formula Recognition:</code></td>
+      <td>LaTeX</td>
+    </tr>
+    <tr>
+      <td>Inline formula</td>
+      <td><code>Text Recognition:</code></td>
+      <td>LaTeX</td>
+    </tr>
+    <tr>
+      <td>Seal</td>
+      <td><code>Seal Recognition:</code></td>
+      <td>Plain text</td>
+    </tr>
+    <tr>
+      <td>Chart</td>
+      <td><code>Chart to Table:</code></td>
+      <td>Table in HTML format(via SDK post-processing)</td>
+    </tr>
+    <tr>
+      <td>Structured information extraction</td>
+      <td>Specified fields</td>
+      <td><code>Extract the "field", .... Format the output as a JSON object with keys: "field", .... If an item is not in the image, use "###".</code></td>
+      <td>JSON</td>
+    </tr>
+  </tbody>
+</table>
+
 ## Related checkpoints
 
 | Format | Hugging Face | ModelScope |