Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,85 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s.imatrix filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-bf16.mmproj filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-f16.mmproj filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-f32.mmproj filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q8_0.mmproj filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Nanonets-OCR-s-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text

Nanonets-OCR-s-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef54e4d185cec22be980a885367330e0fe590dfdb19a906c207afbdee7626c57
+size 6178315808

Nanonets-OCR-s-bf16.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfb2ba0dc6f8931c3efcbd39cc06aea05102384f0af3292bf1a8858dce39687
+size 1338428512

Nanonets-OCR-s-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9bb3c5aa467ed00b4a38f747641da56cebdc6e4ccbd2ec6bbd47e06223c40b
+size 4497317408

Nanonets-OCR-s-f16.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686187fdf5e290af20da64ffb4352a1b988a1d570fa75c1c52751d2cf0a1a62b
+size 1338428512

Nanonets-OCR-s-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d133719928673c4e2a46fa34dc1e80159fb5a6319d56bbed878fdd84659980f8
+size 4497317408

Nanonets-OCR-s-f32.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b292f1dee515b71a931115d7eb7c9f19c39463b131ca114b4ff705b481c83ff
+size 2671758432

Nanonets-OCR-s-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0516c84a7f9d5f996095c6c5b72c1c6b5a03068c345a6badbdc91e3f7a986721
+size 997302112

Nanonets-OCR-s-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5348375e315a9064526913f4fbbc9eb4743bbc63efa2cf02746224f17df3ae11
+size 925179744

Nanonets-OCR-s-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30842d79efae301996e766241189bdb4c1e6f560cd561350c06f548403f45a1f
+size 1199726432

Nanonets-OCR-s-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38407734740af334e45c3927e6de07cacb082553eccd9de828450cd0ed90e146
+size 1146052448

Nanonets-OCR-s-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ba6ef9c770e88a67cca28164a659fad11db09901c93d6697e0bc9c1aaa689a
+size 1111433056

Nanonets-OCR-s-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3eea75723bc0e2ad9831db52bd84ce1dacdae635be7c955d2ab6f17b370137
+size 1026629472

Nanonets-OCR-s-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed03cad207681497d7fa203adae1bdc59dd2db4ee12bf374427bd78902d94570
+size 1523654496

Nanonets-OCR-s-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0f1fdd06622a8e88fa5b96f090cdcdda8fc0aad9b233fb3c8a3abb94bfcc94
+size 1507008352

Nanonets-OCR-s-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0afa262f0656e5ccb78a96e397c23bd110de827baa7dd92c6f24f3ddf1c376
+size 1368825696

Nanonets-OCR-s-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3318333dc59747018f85ae4e12f9d6e66994490aab5df38100e319da72152d8a
+size 1339187040

Nanonets-OCR-s-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ab12fab96d7b1e563ea67944154bc632a5ac34c9c939791e017e6e22869246
+size 1825208160

Nanonets-OCR-s-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ecf62308db8fa6fed2ae540626c9b74c22a148959e14b9bf1ecc150e8ac6f9c
+size 1739093856

Nanonets-OCR-s-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714b43a691cbd8f7ada07552a30216da2e7bedcba68282060e499872711d3e63
+size 1274754912

Nanonets-OCR-s-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2a3a955c64f2ffb757130773dd173f887da9a95e75db1fd9ad43d9acb33474
+size 1233477472

Nanonets-OCR-s-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e03facfb94c3f3f19462db72c0cf7b54fe74f08c1c7dc5aff072fe905a97f72
+size 1590474592

Nanonets-OCR-s-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8a2338bab44685fc203331890a872be1d1479775e084606e59d72d16b2ad3a
+size 1539710816

Nanonets-OCR-s-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cf2b2844257c760152e9f2fc0267d11b7b4479b920f17e195e58c9cb143d0c
+size 1742626656

Nanonets-OCR-s-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30775f206c5ebaf39bc5c4e1cbc1f3373af86a373a9a69ba6510da43a56cf7da
+size 1935482720

Nanonets-OCR-s-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d762a6a86bfe5494c700e4ce95bad9b7f681bb639f3007d0174070599e35bf2
+size 1934096224

Nanonets-OCR-s-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d476a9ef2b494729dbcda39b786ab7d3c5febccef7eaf615578b98298ffd9f
+size 1850111840

Nanonets-OCR-s-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b67296fb2153e8ae365d2fc6262e4182b6456deb60384d444ba7230977a7841
+size 2128338784

Nanonets-OCR-s-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce3a7797a3287be1f710a70d90fc977d76465134f61fcbe2851c71d921a1564
+size 2321194848

Nanonets-OCR-s-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a10d3a615f6ce20873516d69402a1f1ab3202bbbd0b1ff2e3d186152326cade
+size 2229270368

Nanonets-OCR-s-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c16fbda4e52b43964e51e0d434ffa6fa7ef181829403f51b4be45a9a003b72b
+size 2198632288

Nanonets-OCR-s-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f23021dcd10a6a9223d05399df22182c7fc7c96608e68cb1c1ed0d9cfc9f71
+size 2538157920

Nanonets-OCR-s-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06e05871bcbce64e1345e55dff9258fde0285d7138802b97af7102e94910cdb
+size 3285474848

Nanonets-OCR-s-q8_0.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5148d8ff54b32ff6c144ff6e2e3343437bba996b4fec14a3e9d7c4a292d0224e
+size 844758112

Nanonets-OCR-s-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefc4e9d1d1192a4e3257dfd1a3ee22eaa012b0442055bee21b8cc3b4b4daa8d
+size 847427424

Nanonets-OCR-s-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd004b2f07030a446fc27d5cddc216299d8a7677cf72dca1e48bcbd4800de9b9
+size 977483616

Nanonets-OCR-s.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e50bf9ebfcb0e6ab67e45790a23c5358a34be002786407140e8d2b8567289f
+size 3363024

README.md

@@ -0,0 +1,233 @@
+---
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-VL-3B-Instruct
+pipeline_tag: image-text-to-text
+tags:
+- OCR
+- pdf2markdown
+library_name: transformers
+---
+
+# <span style="color: #7FFF7F;">Nanonets-OCR-s GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`bf9087f5`](https://github.com/ggerganov/llama.cpp/commit/bf9087f59aab940cf312b85a67067ce33d9e365a).
+
+
+
+
+
+---
+
+## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
+
+I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
+
+In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:  
+👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+While this does increase model file size, it significantly improves precision for a given quantization level.
+
+### **I'd love your feedback—have you tried this? How does it perform for you?**
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+
+
+Nanonets-OCR-s by [Nanonets](https://nanonets.com) is a powerful, state-of-the-art image-to-markdown OCR model that goes far beyond traditional text extraction. It transforms documents into structured markdown with intelligent content recognition and semantic tagging, making it ideal for downstream processing by Large Language Models (LLMs).
+
+Nanonets-OCR-s is packed with features designed to handle complex documents with ease:
+
+* **LaTeX Equation Recognition:** Automatically converts mathematical equations and formulas into properly formatted LaTeX syntax. It distinguishes between inline (`$...$`) and display (`$$...$$`) equations.
+* **Intelligent Image Description:** Describes images within documents using structured `<img>` tags, making them digestible for LLM processing. It can describe various image types, including logos, charts, graphs and so on, detailing their content, style, and context.
+* **Signature Detection & Isolation:** Identifies and isolates signatures from other text, outputting them within a `<signature>` tag. This is crucial for processing legal and business documents.
+* **Watermark Extraction:** Detects and extracts watermark text from documents, placing it within a `<watermark>` tag.
+* **Smart Checkbox Handling:** Converts form checkboxes and radio buttons into standardized Unicode symbols (`☐`, `☑`, `☒`) for consistent and reliable processing.
+* **Complex Table Extraction:** Accurately extracts complex tables from documents and converts them into both markdown and HTML table formats.
+
+
+📢 [Read the full announcement](https://nanonets.com/research/nanonets-ocr-s) | 🤗 [Hugging Face Space Demo](https://huggingface.co/spaces/Souvik3333/Nanonets-ocr-s)
+
+## Usage
+### Using transformers
+```python
+from PIL import Image
+from transformers import AutoTokenizer, AutoProcessor, AutoModelForImageTextToText
+
+model_path = "nanonets/Nanonets-OCR-s"
+
+model = AutoModelForImageTextToText.from_pretrained(
+    model_path, 
+    torch_dtype="auto", 
+    device_map="auto", 
+    attn_implementation="flash_attention_2"
+)
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+processor = AutoProcessor.from_pretrained(model_path)
+
+
+def ocr_page_with_nanonets_s(image_path, model, processor, max_new_tokens=4096):
+    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."""
+    image = Image.open(image_path)
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": [
+            {"type": "image", "image": f"file://{image_path}"},
+            {"type": "text", "text": prompt},
+        ]},
+    ]
+    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = processor(text=[text], images=[image], padding=True, return_tensors="pt")
+    inputs = inputs.to(model.device)
+    
+    output_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, do_sample=False)
+    generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
+    
+    output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
+    return output_text[0]
+
+image_path = "/path/to/your/document.jpg"
+result = ocr_page_with_nanonets_s(image_path, model, processor, max_new_tokens=15000)
+print(result)
+```
+
+### Using vLLM
+1. Start the vLLM server.
+```bash
+vllm serve nanonets/Nanonets-OCR-s
+```
+2. Predict with the model
+```python
+from openai import OpenAI
+import base64
+
+client = OpenAI(api_key="123", base_url="http://localhost:8000/v1")
+
+model = "nanonets/Nanonets-OCR-s"
+
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+def ocr_page_with_nanonets_s(img_base64):
+    response = client.chat.completions.create(
+        model=model,
+        messages=[
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": f"data:image/png;base64,{img_base64}"},
+                    },
+                    {
+                        "type": "text",
+                        "text": "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.",
+                    },
+                ],
+            }
+        ],
+        temperature=0.0,
+        max_tokens=15000
+    )
+    return response.choices[0].message.content
+
+test_img_path = "/path/to/your/document.jpg"
+img_base64 = encode_image(test_img_path)
+print(ocr_page_with_nanonets_s(img_base64))
+```
+
+### Using docext
+```python
+pip install docext
+python -m docext.app.app --model_name hosted_vllm/nanonets/Nanonets-OCR-s
+```
+Checkout [GitHub](https://github.com/NanoNets/docext/tree/dev/markdown) for more details.
+
+
+## BibTex
+```
+@misc{Nanonets-OCR-S,
+  title={Nanonets-OCR-S: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging},
+  author={Souvik Mandal and Ashish Talewar and Paras Ahuja and Prathamesh Juvatkar},
+  year={2025},
+}
+```
+
+<!--End Original Model Card-->
+
+---
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊