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, dtype="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
```

notlikejoe commited on Jan 16

Commit

b9e6428

verified ·

1 Parent(s): 6b715da

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -118,6 +118,18 @@ The model has been validated to ensure:
 ✅ Model structure matches expected architecture
 ✅ Compatible with Optimum-Intel export
 ✅ Forward pass completes without errors
 ## Limitations

 ✅ Model structure matches expected architecture
 ✅ Compatible with Optimum-Intel export
 ✅ Forward pass completes without errors
+✅ **OpenVINO compatibility fix applied**: Resampler `num_heads=0` issue resolved
+### OpenVINO Compatibility Fix
+This model includes a fix for the OpenVINO loading issue where `num_heads=0` would occur with small `embed_dim` values. The resampler's `num_heads` calculation has been patched to ensure it's always at least 1:
+```python
+# Original: num_heads = embed_dim // 128  # Would be 0 when embed_dim=40
+# Fixed:    num_heads = 1 if embed_dim < 128 else max(1, embed_dim // 128)
+```
+The `modeling_minicpmo.py` file included with this model contains this fix, ensuring compatibility with Optimum-Intel OpenVINO export and loading.
 ## Limitations