Instructions to use bochu/MiniCPM-V-2_6-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bochu/MiniCPM-V-2_6-int4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="bochu/MiniCPM-V-2_6-int4", 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("bochu/MiniCPM-V-2_6-int4", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bochu/MiniCPM-V-2_6-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bochu/MiniCPM-V-2_6-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bochu/MiniCPM-V-2_6-int4",
		"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/bochu/MiniCPM-V-2_6-int4

SGLang

How to use bochu/MiniCPM-V-2_6-int4 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 "bochu/MiniCPM-V-2_6-int4" \
    --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": "bochu/MiniCPM-V-2_6-int4",
		"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 "bochu/MiniCPM-V-2_6-int4" \
        --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": "bochu/MiniCPM-V-2_6-int4",
		"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 bochu/MiniCPM-V-2_6-int4 with Docker Model Runner:
```
docker model run hf.co/bochu/MiniCPM-V-2_6-int4
```

News

[2025.01.14] 🔥🔥 We open source MiniCPM-o 2.6, with significant performance improvement over MiniCPM-V 2.6, and support real-time speech-to-speech conversation and multimodal live streaming. Try it now.

MiniCPM-V 2.6 int4

This is the int4 quantized version of MiniCPM-V 2.6.
Running with int4 version would use lower GPU memory (about 7GB).

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：

Pillow==10.1.0
torch==2.1.2
torchvision==0.16.2
transformers==4.40.0
sentencepiece==0.1.99
accelerate==0.30.1
bitsandbytes==0.43.1

# test.py
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6-int4', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6-int4', trust_remote_code=True)
model.eval()

image = Image.open('xx.jpg').convert('RGB')
question = 'What is in the image?'
msgs = [{'role': 'user', 'content': [image, question]}]

res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer
)
print(res)

## if you want to use streaming, please make sure sampling=True and stream=True
## the model.chat will return a generator
res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    temperature=0.7,
    stream=True
)

generated_text = ""
for new_text in res:
    generated_text += new_text
    print(new_text, flush=True, end='')

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

F32

BF16

Model tree for bochu/MiniCPM-V-2_6-int4

Base model

openbmb/MiniCPM-V-2_6

Quantized

(13)

this model

Duplicated from openbmb/MiniCPM-V-2_6-int4

bochu
/

MiniCPM-V-2_6-int4

News

MiniCPM-V 2.6 int4

Usage

Model tree for bochu/MiniCPM-V-2_6-int4

Dataset used to train bochu/MiniCPM-V-2_6-int4