Instructions to use wirehead82/function-gemma-mobile-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wirehead82/function-gemma-mobile-agent with Transformers:

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

pipe = pipeline("text-generation", model="wirehead82/function-gemma-mobile-agent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wirehead82/function-gemma-mobile-agent")
model = AutoModelForCausalLM.from_pretrained("wirehead82/function-gemma-mobile-agent", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wirehead82/function-gemma-mobile-agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wirehead82/function-gemma-mobile-agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wirehead82/function-gemma-mobile-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wirehead82/function-gemma-mobile-agent

SGLang

How to use wirehead82/function-gemma-mobile-agent 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 "wirehead82/function-gemma-mobile-agent" \
    --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": "wirehead82/function-gemma-mobile-agent",
		"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 "wirehead82/function-gemma-mobile-agent" \
        --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": "wirehead82/function-gemma-mobile-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wirehead82/function-gemma-mobile-agent with Docker Model Runner:
```
docker model run hf.co/wirehead82/function-gemma-mobile-agent
```

wirehead82 commited on Dec 23, 2025

Commit

24b2614

verified ·

1 Parent(s): fd1b1fa

Upload adapter_config.json with huggingface_hub

Browse files

Files changed (1) hide show

adapter_config.json +18 -0

adapter_config.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "base_model_name_or_path": "google/gemma-3-270m-it",
+  "peft_type": "LORA",
+  "task_type": "CAUSAL_LM",
+  "r": 1,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "lora_alpha": 1,
+  "lora_dropout": 0.05,
+  "fan_in_fan_out": false,
+  "bias": "none",
+  "modules_to_save": null,
+  "init_lora_weights": true
+}