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

Libraries

How to use 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="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("tiny-random/minicpm-v-4_5", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 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 "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": "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/tiny-random/minicpm-v-4_5

SGLang

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

minicpm-v-4_5 / config.json

yujiepan

Upload folder using huggingface_hub

33b2bbb verified 10 months ago

Raw

History Blame Contribute Delete

1.76 kB

	{
	"architectures": [
	"MiniCPMV"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "openbmb/MiniCPM-V-4_5--configuration_minicpm.MiniCPMVConfig",
	"AutoModel": "openbmb/MiniCPM-V-4_5--modeling_minicpmv.MiniCPMV",
	"AutoModelForCausalLM": "openbmb/MiniCPM-V-4_5--modeling_minicpmv.MiniCPMV"
	},
	"batch_3d_resampler": true,
	"batch_vision_input": true,
	"bos_token_id": 151643,
	"drop_vision_last_layer": false,
	"eos_token_id": 151645,
	"head_dim": 32,
	"hidden_act": "silu",
	"hidden_size": 128,
	"image_size": 448,
	"initializer_range": 0.02,
	"intermediate_size": 128,
	"layer_types": [
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 40960,
	"max_window_layers": 36,
	"model_type": "minicpmv",
	"num_attention_heads": 2,
	"num_hidden_layers": 2,
	"num_key_value_heads": 1,
	"patch_size": 14,
	"query_num": 64,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000,
	"slice_config": {
	"max_slice_nums": 9,
	"model_type": "minicpmv",
	"patch_size": 14,
	"scale_resolution": 448
	},
	"slice_mode": true,
	"sliding_window": null,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.56.0.dev0",
	"use_cache": true,
	"use_image_id": true,
	"use_sliding_window": false,
	"version": 4.5,
	"vision_batch_size": 16,
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 64,
	"image_size": 980,
	"intermediate_size": 128,
	"layer_norm_eps": 1e-06,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 2,
	"num_channels": 3,
	"num_hidden_layers": 2,
	"patch_size": 14
	},
	"vocab_size": 151748
	}