Instructions to use notlikejoe/tiny-random-MiniCPM-o-2_6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use notlikejoe/tiny-random-MiniCPM-o-2_6 with Transformers:

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

pipe = pipeline("text-generation", model="notlikejoe/tiny-random-MiniCPM-o-2_6", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("notlikejoe/tiny-random-MiniCPM-o-2_6", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use notlikejoe/tiny-random-MiniCPM-o-2_6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "notlikejoe/tiny-random-MiniCPM-o-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": "notlikejoe/tiny-random-MiniCPM-o-2_6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/notlikejoe/tiny-random-MiniCPM-o-2_6

SGLang

How to use notlikejoe/tiny-random-MiniCPM-o-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 "notlikejoe/tiny-random-MiniCPM-o-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": "notlikejoe/tiny-random-MiniCPM-o-2_6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "notlikejoe/tiny-random-MiniCPM-o-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": "notlikejoe/tiny-random-MiniCPM-o-2_6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use notlikejoe/tiny-random-MiniCPM-o-2_6 with Docker Model Runner:
```
docker model run hf.co/notlikejoe/tiny-random-MiniCPM-o-2_6
```

tiny-random-MiniCPM-o-2_6 / preprocessor_config.json

notlikejoe

Upload folder using huggingface_hub

45af4b6 verified 7 months ago

Raw

History Blame Contribute Delete

1.1 kB

	{
	"auto_map": {
	"AutoImageProcessor": "openbmb/MiniCPM-o-2_6--image_processing_minicpmv.MiniCPMVImageProcessor",
	"AutoProcessor": "openbmb/MiniCPM-o-2_6--processing_minicpmo.MiniCPMOProcessor"
	},
	"chunk_length": 30,
	"dither": 0.0,
	"feature_extractor_type": "WhisperFeatureExtractor",
	"feature_size": 80,
	"hop_length": 160,
	"im_end": "</image>",
	"im_id_end": "</image_id>",
	"im_id_start": "<image_id>",
	"im_start": "<image>",
	"image_feature_size": 64,
	"image_processor_type": "MiniCPMVImageProcessor",
	"max_slice_nums": 9,
	"n_fft": 400,
	"n_samples": 480000,
	"nb_max_frames": 3000,
	"norm_mean": [
	0.5,
	0.5,
	0.5
	],
	"norm_std": [
	0.5,
	0.5,
	0.5
	],
	"padding_side": "right",
	"padding_value": 0.0,
	"patch_size": 14,
	"processor_class": "MiniCPMOProcessor",
	"return_attention_mask": false,
	"sampling_rate": 16000,
	"scale_resolution": 448,
	"slice_end": "</slice>",
	"slice_mode": true,
	"slice_start": "<slice>",
	"unk": "<unk>",
	"use_image_id": true,
	"version": 2.6
	}