update system prompt

README.md

@@ -6,6 +6,8 @@ base_model: nanonets/Nanonets-OCR-s
 pipeline_tag: image-text-to-text
 tags:
   - OCR
+base_model_relation: quantized
+quantized_by: benhaotang
 ---
 
 Quatized [nanonets/Nanonets-OCR-s](https://huggingface.co/nanonets/Nanonets-OCR-s) with llama.cpp commit fb85a288
@@ -13,5 +15,18 @@ Quatized [nanonets/Nanonets-OCR-s](https://huggingface.co/nanonets/Nanonets-OCR-
 Multiple ways to use:
 
 - run with llama.cpp: `./llama-server -m "Nanonets-OCR-s-Q4_K_M.gguf" --mmproj "mmproj-Nanonets-OCR-s.gguf"`
-- use with lmstudio: just pull from `benhaotang/Nanonets-OCR-s-GGUF` **(Warning: change chat template to chatml in model settings)**
-- use with ollama: `ollama run benhaotang/Nanonets-OCR-s`
+- use with lmstudio: just pull from `benhaotang/Nanonets-OCR-s-GGUF` **(Warning‼️: change chat template to chatml in model settings)**
+- use with ollama: `ollama run benhaotang/Nanonets-OCR-s`
+
+Suggested system prompt:
+
+```
+Extract the text from the above document as if you were reading it naturally.
+Return the tables in html format. Return the equations in LaTeX representation.
+If there is an image in the document and image caption is not present,
+add a small description of the image inside the <img></img> tag;
+otherwise, add the image caption inside <img></img>.
+Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>.
+Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>.
+Prefer using ☐ and ☑ for check boxes.
+```