Image-Text-to-Text
Transformers
Safetensors
minicpmv4_6
minicpm-v
multimodal
On-Device Model
lightweight
conversational
Instructions to use openbmb/MiniCPM-V-4.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-V-4.6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="openbmb/MiniCPM-V-4.6") 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 AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("openbmb/MiniCPM-V-4.6") model = AutoModelForImageTextToText.from_pretrained("openbmb/MiniCPM-V-4.6") 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?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use openbmb/MiniCPM-V-4.6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/MiniCPM-V-4.6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openbmb/MiniCPM-V-4.6", "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/openbmb/MiniCPM-V-4.6
- SGLang
How to use openbmb/MiniCPM-V-4.6 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 "openbmb/MiniCPM-V-4.6" \ --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": "openbmb/MiniCPM-V-4.6", "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 "openbmb/MiniCPM-V-4.6" \ --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": "openbmb/MiniCPM-V-4.6", "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 openbmb/MiniCPM-V-4.6 with Docker Model Runner:
docker model run hf.co/openbmb/MiniCPM-V-4.6
feat: add tool_call example
#5
by airlsyn - opened
README.md
CHANGED
|
@@ -249,6 +249,57 @@ curl -s http://localhost:8000/v1/chat/completions \
|
|
| 249 |
}'
|
| 250 |
```
|
| 251 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
#### Handling Escaped Newlines in Model Outputs <!-- omit in toc -->
|
| 253 |
|
| 254 |
In some cases, the model might output escaped newline characters `\n` as string literals instead of actual newlines. To render the text correctly, especially in UI layers, you can use the following utility function. This function carefully replaces literal `\n` with real newlines while protecting scenarios where `\n` has specific semantic meaning.
|
|
|
|
| 249 |
}'
|
| 250 |
```
|
| 251 |
|
| 252 |
+
Tool calling example:
|
| 253 |
+
|
| 254 |
+
```bash
|
| 255 |
+
curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{
|
| 256 |
+
"model": "openbmb/MiniCPM-V-4.6",
|
| 257 |
+
"messages": [{"role": "user", "content": [
|
| 258 |
+
{"type": "text", "text": "the weather of Beijing"}
|
| 259 |
+
]}],
|
| 260 |
+
"tools": [{
|
| 261 |
+
"type": "function",
|
| 262 |
+
"function": {
|
| 263 |
+
"name": "get_weather",
|
| 264 |
+
"description": "Get the current weather for a given location",
|
| 265 |
+
"parameters": {
|
| 266 |
+
"type": "object",
|
| 267 |
+
"properties": {
|
| 268 |
+
"location": {"type": "string", "description": "City name"}
|
| 269 |
+
},
|
| 270 |
+
"required": ["location"]
|
| 271 |
+
}
|
| 272 |
+
}
|
| 273 |
+
}]
|
| 274 |
+
}'
|
| 275 |
+
```
|
| 276 |
+
|
| 277 |
+
The model returns a natural-language explanation followed by a structured <tool_call> block embedded in the content field. Note that a dedicated tool call parser for this format has not yet been added to the transformers library, so the tool calls need to be extracted manually via regex for now.
|
| 278 |
+
|
| 279 |
+
```
|
| 280 |
+
{
|
| 281 |
+
"id": "f4f09c7d-8045-4cb1-ade9-07aa5dee637d",
|
| 282 |
+
"choices": [
|
| 283 |
+
{
|
| 284 |
+
"finish_reason": "stop",
|
| 285 |
+
"index": 0,
|
| 286 |
+
"message": {
|
| 287 |
+
"content": "I need to check the current weather for Beijing, so I will call the get_weather function.\n\n<tool_call>\n<function=get_weather>\n<parameter=location>\nBeijing\n</parameter>\n</function>\n</tool_call>",
|
| 288 |
+
"role": "assistant"
|
| 289 |
+
}
|
| 290 |
+
}
|
| 291 |
+
],
|
| 292 |
+
"created": 1778748859,
|
| 293 |
+
"model": "openbmb/MiniCPM-V-4.6@main",
|
| 294 |
+
"object": "chat.completion",
|
| 295 |
+
"usage": {
|
| 296 |
+
"completion_tokens": 47,
|
| 297 |
+
"prompt_tokens": 283,
|
| 298 |
+
"total_tokens": 330
|
| 299 |
+
}
|
| 300 |
+
}
|
| 301 |
+
```
|
| 302 |
+
|
| 303 |
#### Handling Escaped Newlines in Model Outputs <!-- omit in toc -->
|
| 304 |
|
| 305 |
In some cases, the model might output escaped newline characters `\n` as string literals instead of actual newlines. To render the text correctly, especially in UI layers, you can use the following utility function. This function carefully replaces literal `\n` with real newlines while protecting scenarios where `\n` has specific semantic meaning.
|