Instructions to use openbmb/MiniCPM-V-2_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-V-2_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-2_6", 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-2_6", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM-V-2_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-2_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-2_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-2_6

SGLang

How to use openbmb/MiniCPM-V-2_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-2_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-2_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-2_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-2_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-2_6 with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-2_6
```

Error: Matmul multiplication error

#29

by supercharge19 - opened Sep 20, 2024

Discussion

supercharge19

Sep 20, 2024

•

edited Sep 20, 2024

Got this error in colab with T4: Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 2024, in generate
result = self._sample(
File "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py", line 2982, in _sample
outputs = self(**model_inputs, return_dict=True)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/models/qwen2/modeling_qwen2.py", line 1104, in forward
outputs = self.model(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/models/qwen2/modeling_qwen2.py", line 915, in forward
layer_outputs = decoder_layer(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/models/qwen2/modeling_qwen2.py", line 655, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/transformers/models/qwen2/modeling_qwen2.py", line 544, in forward
value_states = self.v_proj(hidden_states)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/accelerate/hooks.py", line 170, in new_forward
output = module._old_forward(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/nn/modules.py", line 817, in forward
out = bnb.matmul(x, self.weight, bias=self.bias, state=self.state)
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/_functions.py", line 556, in matmul
return MatMul8bitLt.apply(A, B, out, bias, state)
File "/usr/local/lib/python3.10/dist-packages/torch/autograd/function.py", line 574, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "/usr/local/lib/python3.10/dist-packages/bitsandbytes/autograd/_functions.py", line 415, in forward
output += torch.matmul(subA, state.subB)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x9 and 7x512)

My bits and bytes config is:

# Configuration for 8-bit quantization
bnb_config = BitsAndBytesConfig(load_in_8bit=True)

# Load the model with 8-bit quantization
model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True,
                                 attn_implementation='sdpa', quantization_config=bnb_config)

model = model.eval()  # Set the model to evaluation mode

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True)

I tried same config with another image and it worked, and it also worked for same image but different prompt, but that prompt was giving useless output and hallucinations is also a problem unless you can fix that with right prompt.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment