Instructions to use facebook/MobileLLM-350M-layer-share with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use facebook/MobileLLM-350M-layer-share with Transformers:

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

pipe = pipeline("text-generation", model="facebook/MobileLLM-350M-layer-share", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("facebook/MobileLLM-350M-layer-share", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use facebook/MobileLLM-350M-layer-share with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "facebook/MobileLLM-350M-layer-share"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/MobileLLM-350M-layer-share",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/facebook/MobileLLM-350M-layer-share

SGLang

How to use facebook/MobileLLM-350M-layer-share 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-350M-layer-share" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/MobileLLM-350M-layer-share",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-350M-layer-share" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/MobileLLM-350M-layer-share",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use facebook/MobileLLM-350M-layer-share with Docker Model Runner:
```
docker model run hf.co/facebook/MobileLLM-350M-layer-share
```

MobileLLM-350M-LS: Unused and Uninitialized Weights, Repeated Output During Generation

by Boxp - opened Nov 25, 2024

Discussion

Boxp

Nov 25, 2024

Description

When using MobileLLM-350M-LS with transformers library, I encountered the following issues:

Warnings:
- Unused weights: lm_head.weight.
- Reinitialized weights: model.embed_tokens.weight.

Output Issues:

Generated text contains excessive repetition. For example:

Hello! Who are you? Below are some of the questions we ask new members.
What is your name? What is your birthday? What is your birthday? ...

Environment

Transformers version: 4.44.0
Python version: 3.11

Code

from transformers import AutoTokenizer, AutoModelForCausalLM

def infer_mobilellm():
    model_dir = "/nfs/300-MT-Pro/model/huggingface/MobileLLM-350M-LS"
    tokenizer = AutoTokenizer.from_pretrained(model_dir, use_fast=False)
    model = AutoModelForCausalLM.from_pretrained(model_dir, trust_remote_code=True)

    input_text = "Hello! Who are you?"
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=100)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))

infer_mobilellm()

Questions

What is the correct way to initialize and perform inference with MobileLLM-350M-LS?

zechunliu

Feb 14, 2025

Hi, thank you for raising this issue! The lm_head.weight is the same as model.embed_tokens.weight, so loading either of them should be fine.

The model is a pre-trained model, not a chat-finetuned model. Therefore, it can only complete sentences, not answer questions. Does that make sense?

For repeated sentences, you can try setting repetition_penalty=1.5; this will help avoid generating repeated outputs.

zechunliu changed discussion status to closed Feb 14, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment