Instructions to use optimum-intel-internal-testing/tiny-random-minicpm-v-4_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use optimum-intel-internal-testing/tiny-random-minicpm-v-4_5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="optimum-intel-internal-testing/tiny-random-minicpm-v-4_5", 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("optimum-intel-internal-testing/tiny-random-minicpm-v-4_5", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use optimum-intel-internal-testing/tiny-random-minicpm-v-4_5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "optimum-intel-internal-testing/tiny-random-minicpm-v-4_5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "optimum-intel-internal-testing/tiny-random-minicpm-v-4_5",
		"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/optimum-intel-internal-testing/tiny-random-minicpm-v-4_5

SGLang

How to use optimum-intel-internal-testing/tiny-random-minicpm-v-4_5 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 "optimum-intel-internal-testing/tiny-random-minicpm-v-4_5" \
    --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": "optimum-intel-internal-testing/tiny-random-minicpm-v-4_5",
		"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 "optimum-intel-internal-testing/tiny-random-minicpm-v-4_5" \
        --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": "optimum-intel-internal-testing/tiny-random-minicpm-v-4_5",
		"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 optimum-intel-internal-testing/tiny-random-minicpm-v-4_5 with Docker Model Runner:
```
docker model run hf.co/optimum-intel-internal-testing/tiny-random-minicpm-v-4_5
```

tiny-random-minicpm-v-4_5

File size: 979 Bytes

67088cf

{
  "auto_map": {
    "AutoImageProcessor": "openbmb/MiniCPM-V-4_5--image_processing_minicpmv.MiniCPMVImageProcessor",
    "AutoProcessor": "openbmb/MiniCPM-V-4_5--processing_minicpmv.MiniCPMVProcessor"
  },
  "im_end": "</image>",
  "im_end_token": "</image>",
  "im_id_end": "</image_id>",
  "im_id_start": "<image_id>",
  "im_start": "<image>",
  "im_start_token": "<image>",
  "image_feature_size": 64,
  "image_processor_type": "MiniCPMVImageProcessor",
  "max_slice_nums": 9,
  "mean": [
    0.5,
    0.5,
    0.5
  ],
  "norm_mean": [
    0.5,
    0.5,
    0.5
  ],
  "norm_std": [
    0.5,
    0.5,
    0.5
  ],
  "patch_size": 14,
  "processor_class": "MiniCPMVProcessor",
  "scale_resolution": 448,
  "slice_end": "</slice>",
  "slice_end_token": "</slice>",
  "slice_mode": true,
  "slice_start": "<slice>",
  "slice_start_token": "<slice>",
  "std": [
    0.5,
    0.5,
    0.5
  ],
  "unk": "<unk>",
  "unk_token": "<unk>",
  "use_image_id": true,
  "version": 2.6
}