Image-Text-to-Text
Transformers
Safetensors
multilingual
minicpmv
feature-extraction
minicpm-v
vision
ocr
multi-image
video
custom_code
conversational
Instructions to use openbmb/MiniCPM-V-4_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/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="openbmb/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("openbmb/MiniCPM-V-4_5", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use openbmb/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 "openbmb/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": "openbmb/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/openbmb/MiniCPM-V-4_5
- SGLang
How to use openbmb/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 "openbmb/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": "openbmb/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 "openbmb/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": "openbmb/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 openbmb/MiniCPM-V-4_5 with Docker Model Runner:
docker model run hf.co/openbmb/MiniCPM-V-4_5
Fix data parsing in forward() method
#18
by bialykostek - opened
- modeling_minicpmv.py +24 -0
modeling_minicpmv.py
CHANGED
|
@@ -203,6 +203,30 @@ class MiniCPMV(MiniCPMVPreTrainedModel):
|
|
| 203 |
|
| 204 |
|
| 205 |
def forward(self, data, **kwargs):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
vllm_embedding, vision_hidden_states = self.get_vllm_embedding(data)
|
| 207 |
|
| 208 |
position_ids = data["position_ids"]
|
|
|
|
| 203 |
|
| 204 |
|
| 205 |
def forward(self, data, **kwargs):
|
| 206 |
+
if isinstance(data, torch.Tensor):
|
| 207 |
+
attention_mask = torch.ones_like(data, dtype=torch.bool)
|
| 208 |
+
kwargs = {'attention_mask': attention_mask}
|
| 209 |
+
return self.llm(
|
| 210 |
+
input_ids=data,
|
| 211 |
+
**kwargs
|
| 212 |
+
)
|
| 213 |
+
|
| 214 |
+
if data is None:
|
| 215 |
+
data = {
|
| 216 |
+
"input_ids": kwargs.pop("input_ids", None),
|
| 217 |
+
"pixel_values": kwargs.pop("pixel_values", None),
|
| 218 |
+
"image_bound": kwargs.pop("image_bound", None),
|
| 219 |
+
"tgt_sizes": kwargs.pop("tgt_sizes", None),
|
| 220 |
+
"position_ids": kwargs.pop("position_ids", None),
|
| 221 |
+
}
|
| 222 |
+
else:
|
| 223 |
+
kwargs.pop("input_ids", None)
|
| 224 |
+
kwargs.pop("pixel_values", None)
|
| 225 |
+
kwargs.pop("image_bound", None)
|
| 226 |
+
kwargs.pop("tgt_sizes", None)
|
| 227 |
+
kwargs.pop("position_ids", None)
|
| 228 |
+
kwargs.pop("inputs_embeds", None)
|
| 229 |
+
|
| 230 |
vllm_embedding, vision_hidden_states = self.get_vllm_embedding(data)
|
| 231 |
|
| 232 |
position_ids = data["position_ids"]
|