Instructions to use CTW-g123/MiniCPM_layout with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CTW-g123/MiniCPM_layout with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="CTW-g123/MiniCPM_layout", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("CTW-g123/MiniCPM_layout", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CTW-g123/MiniCPM_layout with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CTW-g123/MiniCPM_layout"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CTW-g123/MiniCPM_layout",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/CTW-g123/MiniCPM_layout

SGLang

How to use CTW-g123/MiniCPM_layout with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "CTW-g123/MiniCPM_layout" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CTW-g123/MiniCPM_layout",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "CTW-g123/MiniCPM_layout" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CTW-g123/MiniCPM_layout",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use CTW-g123/MiniCPM_layout with Docker Model Runner:
```
docker model run hf.co/CTW-g123/MiniCPM_layout
```

MiniCPM_layout / preprocessor_config.json

ctw-ai

Upload folder using huggingface_hub (#1)

eb69390 verified over 1 year ago

raw

history blame contribute delete

714 Bytes

	{
	"image_processor_type": "MiniCPMVImageProcessor",
	"auto_map": {
	"AutoProcessor": "processing_minicpmv.MiniCPMVProcessor",
	"AutoImageProcessor": "image_processing_minicpmv.MiniCPMVImageProcessor"
	},
	"processor_class": "MiniCPMVProcessor",
	"max_slice_nums": 9,
	"scale_resolution": 448,
	"patch_size": 14,
	"use_image_id": true,
	"image_feature_size": 64,
	"im_start": "<image>",
	"im_end": "</image>",
	"slice_start": "<slice>",
	"slice_end": "</slice>",
	"unk": "<unk>",
	"im_id_start": "<image_id>",
	"im_id_end": "</image_id>",
	"slice_mode": true,
	"norm_mean": [0.5, 0.5, 0.5],
	"norm_std": [0.5, 0.5, 0.5],
	"version": 2.6
	}