Instructions to use mtgv/MobileLLaMA-1.4B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mtgv/MobileLLaMA-1.4B-Base with Transformers:

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

pipe = pipeline("text-generation", model="mtgv/MobileLLaMA-1.4B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mtgv/MobileLLaMA-1.4B-Base")
model = AutoModelForCausalLM.from_pretrained("mtgv/MobileLLaMA-1.4B-Base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mtgv/MobileLLaMA-1.4B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mtgv/MobileLLaMA-1.4B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mtgv/MobileLLaMA-1.4B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mtgv/MobileLLaMA-1.4B-Base

SGLang

How to use mtgv/MobileLLaMA-1.4B-Base 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 "mtgv/MobileLLaMA-1.4B-Base" \
    --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": "mtgv/MobileLLaMA-1.4B-Base",
		"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 "mtgv/MobileLLaMA-1.4B-Base" \
        --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": "mtgv/MobileLLaMA-1.4B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mtgv/MobileLLaMA-1.4B-Base with Docker Model Runner:
```
docker model run hf.co/mtgv/MobileLLaMA-1.4B-Base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Summery

MobileLLaMA-1.4B-Base is a Transformer with 1.4B billon paramters. We downscale LLaMA to facilitate the off-the-shelf deployment. To make our work reproducible, all the models are trained on 1.3T tokens from the RedPajama v1 dataset only. This benefits further research by enabling controlled experiments.

We extensively assess our models on two standard natural language benchmarks, for language understanding and common sense reasoning respectively. Experimental results show that our MobileLLaMA 1.4B is on par with the most recent opensource models.