Update README.md

README.md

@@ -1,3 +1,170 @@
 ---
 license: apache-2.0
+base_model:
+- opendatalab/MinerU2.5-Pro-2605-1.2B
+pipeline_tag: image-text-to-text
 ---
+The `MinerU2.5-Pro` is now supported in `llama-cpp-python`. This project provides a test GGUF file.
+
+`llama-cpp-python`: https://github.com/JamePeng/llama-cpp-python
+
+Code example:
+```python
+from llama_cpp import Llama
+from llama_cpp.llama_chat_format import Qwen25VLChatHandler
+import base64
+import os
+
+# Model and multimodal projection paths
+MODEL_PATH = r".\MinerU2.5-Pro-2605-1.2b-BF16.gguf"
+MMPROJ_PATH = r".\mmproj-MinerU2.5-Pro-2605-BF16.gguf"
+
+# Initialize the Llama model with vision support
+llm = Llama(
+    model_path=MODEL_PATH,
+    chat_handler=Qwen25VLChatHandler(
+        clip_model_path=MMPROJ_PATH,
+        verbose=True
+    ),
+    n_gpu_layers=-1,    # Use all available GPU layers
+    n_ctx = 20480,          # Context window size
+    n_batch=2048,
+    verbose=False
+)
+
+# Comprehensive MIME type mapping (updated as of 2025)
+# Based on Pillow 10.x+ "Fully Supported" (Read & Write) formats
+# Reference: IANA official media types + common real-world usage
+# See: https://pillow.readthedocs.io/en/stable/handbook/image-file-formats.html
+_IMAGE_MIME_TYPES = {
+    # Most common formats
+    '.png':  'image/png',
+    '.jpg':  'image/jpeg',
+    '.jpeg': 'image/jpeg',
+    '.gif':  'image/gif',
+    '.webp': 'image/webp',
+
+    # Next-generation formats
+    '.avif': 'image/avif',
+    '.jp2':  'image/jp2',
+    '.j2k':  'image/jp2',
+    '.jpx':  'image/jp2',
+
+    # Legacy / Windows formats
+    '.bmp':  'image/bmp',
+    '.ico':  'image/x-icon',
+    '.pcx':  'image/x-pcx',
+    '.tga':  'image/x-tga',
+    '.icns': 'image/icns',
+
+    # Professional / Scientific imaging
+    '.tif':  'image/tiff',
+    '.tiff': 'image/tiff',
+    '.eps':  'application/postscript',
+    '.dds':  'image/vnd-ms.dds',
+    '.dib':  'image/dib',
+    '.sgi':  'image/sgi',
+
+    # Portable Map formats (PPM/PGM/PBM)
+    '.pbm':  'image/x-portable-bitmap',
+    '.pgm':  'image/x-portable-graymap',
+    '.ppm':  'image/x-portable-pixmap',
+
+    # Miscellaneous / Older formats
+    '.xbm':  'image/x-xbitmap',
+    '.mpo':  'image/mpo',
+    '.msp':  'image/msp',
+    '.im':   'image/x-pillow-im',
+    '.qoi':  'image/qoi',
+}
+
+def image_to_base64_data_uri(
+    file_path: str,
+    *,
+    fallback_mime: str = "application/octet-stream"
+) -> str:
+    """
+    Convert a local image file to a base64-encoded data URI with the correct MIME type.
+
+    Supports 20+ image formats (PNG, JPEG, WebP, AVIF, HEIC, SVG, BMP, ICO, TIFF, etc.).
+
+    Args:
+        file_path: Path to the image file on disk.
+        fallback_mime: MIME type used when the file extension is unknown.
+
+    Returns:
+        A valid data URI string (e.g., data:image/webp;base64,...).
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+        OSError: If reading the file fails.
+    """
+    if not os.path.isfile(file_path):
+        raise FileNotFoundError(f"Image file not found: {file_path}")
+
+    extension = os.path.splitext(file_path)[1].lower()
+    mime_type = _IMAGE_MIME_TYPES.get(extension, fallback_mime)
+
+    if mime_type == fallback_mime:
+        print(f"Warning: Unknown extension '{extension}' for '{file_path}'. "
+              f"Using fallback MIME type: {fallback_mime}")
+
+    try:
+        with open(file_path, "rb") as img_file:
+            encoded_data = base64.b64encode(img_file.read()).decode("utf-8")
+    except OSError as e:
+        raise OSError(f"Failed to read image file '{file_path}': {e}") from e
+
+    return f"data:{mime_type};base64,{encoded_data}"
+
+
+# ========================
+# Main image processing & inference section
+# ========================
+
+# 1. List of image paths you want to analyze (supports mixed formats)
+image_paths = [
+    r'./book.jpg',
+]
+
+# 2. Container for message content (each image + final text prompt)
+user_content = []
+
+# 3. Convert every image to a properly formatted data URI message
+for path in image_paths:
+    data_uri = image_to_base64_data_uri(path)
+    user_content.append({
+        "type": "image_url",
+        "image_url": {"url": data_uri}
+    })
+
+DEFAULT_PROMPTS: dict[str, str] = {
+    "table": "\nTable Recognition:",
+    "equation": "\nFormula Recognition:",
+    "image": "\nImage Analysis:",
+    "chart": "\nImage Analysis:",
+    "[default]": "\nText Recognition:",
+    "[layout]": "\nLayout Detection:",
+    "[cross_page_table_merge]": "",  # prompt is dynamic, built from table content
+}
+
+# 4. Append the text instruction (appears after all images in the message)
+user_content.append({
+    "type": "text",
+    "text": DEFAULT_PROMPTS['[default]']  # You can change the prompt as needed
+})
+
+# 5. Perform chat completion with vision
+response = llm.create_chat_completion(
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": user_content}
+    ],
+    max_tokens=10240,
+    present_penalty=1.0,
+    frequency_penalty=0.05
+)
+
+# 6. Print the model's reply
+print(response["choices"][0]["message"]["content"])
+```