Instructions to use facebook/MobileLLM-Pro-base-int4-cpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use facebook/MobileLLM-Pro-base-int4-cpu with Transformers:

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

pipe = pipeline("text-generation", model="facebook/MobileLLM-Pro-base-int4-cpu", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("facebook/MobileLLM-Pro-base-int4-cpu", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("facebook/MobileLLM-Pro-base-int4-cpu", trust_remote_code=True)
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use facebook/MobileLLM-Pro-base-int4-cpu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "facebook/MobileLLM-Pro-base-int4-cpu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/MobileLLM-Pro-base-int4-cpu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/facebook/MobileLLM-Pro-base-int4-cpu

SGLang

How to use facebook/MobileLLM-Pro-base-int4-cpu 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 "facebook/MobileLLM-Pro-base-int4-cpu" \
    --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": "facebook/MobileLLM-Pro-base-int4-cpu",
		"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 "facebook/MobileLLM-Pro-base-int4-cpu" \
        --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": "facebook/MobileLLM-Pro-base-int4-cpu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use facebook/MobileLLM-Pro-base-int4-cpu with Docker Model Runner:
```
docker model run hf.co/facebook/MobileLLM-Pro-base-int4-cpu
```

You need to agree to share your contact information to access this model

The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.

Gated model

You can list files but not access them

Preview of files found in this repository

facebook
/

MobileLLM-Pro-base-int4-cpu

You need to agree to share your contact information to access this model

Gated model

You can list files but not access them

Detected Pickle imports (3)

You need to agree to share your contact information to access this model

Gated model You can list files but not access them

Detected Pickle imports (3)

Gated model

You can list files but not access them