Instructions to use ClarkBear/gemma4-e2b-mobile-actions-200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClarkBear/gemma4-e2b-mobile-actions-200 with Transformers:

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

pipe = pipeline("text-generation", model="ClarkBear/gemma4-e2b-mobile-actions-200")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ClarkBear/gemma4-e2b-mobile-actions-200")
model = AutoModelForMultimodalLM.from_pretrained("ClarkBear/gemma4-e2b-mobile-actions-200", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ClarkBear/gemma4-e2b-mobile-actions-200 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClarkBear/gemma4-e2b-mobile-actions-200"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClarkBear/gemma4-e2b-mobile-actions-200",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ClarkBear/gemma4-e2b-mobile-actions-200

SGLang

How to use ClarkBear/gemma4-e2b-mobile-actions-200 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 "ClarkBear/gemma4-e2b-mobile-actions-200" \
    --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": "ClarkBear/gemma4-e2b-mobile-actions-200",
		"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 "ClarkBear/gemma4-e2b-mobile-actions-200" \
        --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": "ClarkBear/gemma4-e2b-mobile-actions-200",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ClarkBear/gemma4-e2b-mobile-actions-200 with Docker Model Runner:
```
docker model run hf.co/ClarkBear/gemma4-e2b-mobile-actions-200
```

ClarkBear commited on Jun 25

Commit

0698cdb

verified ·

1 Parent(s): 1ab77a7

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -133,6 +133,18 @@ generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 print(generator(prompt, max_new_tokens=160, do_sample=False)[0]["generated_text"])
 ```
 ## Limitations
 This is an experimental small-data fine-tune.

 print(generator(prompt, max_new_tokens=160, do_sample=False)[0]["generated_text"])
 ```
+## Examples
+This repository includes runnable examples:
+```bash
+python examples/run_transformers.py \
+  --model-id ClarkBear/gemma4-e2b-mobile-actions-200 \
+  --prompt "Turn on the flashlight"
+```
+Example prompts are available in `examples/prompts.jsonl`.
 ## Limitations
 This is an experimental small-data fine-tune.