Instructions to use mtgv/MobileLLaMA-2.7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mtgv/MobileLLaMA-2.7B-Base with Transformers:

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

pipe = pipeline("text-generation", model="mtgv/MobileLLaMA-2.7B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mtgv/MobileLLaMA-2.7B-Base")
model = AutoModelForCausalLM.from_pretrained("mtgv/MobileLLaMA-2.7B-Base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mtgv/MobileLLaMA-2.7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mtgv/MobileLLaMA-2.7B-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-2.7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mtgv/MobileLLaMA-2.7B-Base

SGLang

How to use mtgv/MobileLLaMA-2.7B-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-2.7B-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-2.7B-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-2.7B-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-2.7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mtgv/MobileLLaMA-2.7B-Base with Docker Model Runner:
```
docker model run hf.co/mtgv/MobileLLaMA-2.7B-Base
```

mtgv commited on Dec 29, 2023

Commit

6e7971e

1 Parent(s): 89345f8

Create README.md

Browse files

Files changed (1) hide show

README.md +13 -0

README.md ADDED Viewed

	@@ -0,0 +1,13 @@

+# Model Summery
+MobileLLaMA-2.7B-Base is a Transformer with 2.7B 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](https://www.together.ai/blog/redpajama) 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 is on par with the most recent opensource models. MobileLLaMA 2.7B also demonstrates competitive performance to INCITE 3B (V1) and OpenLLaMA 3B (V1), while being about 40% faster than OpenLLaMA 3B on a Snapdragon 888 CPU as shown in our [paper](https://arxiv.org/abs/2312.16886) Table 5.
+# Model Sources
+- Repository: https://github.com/Meituan-AutoML/MobileVLM
+- Paper: https://arxiv.org/abs/2312.16886
+# How to Get Started with the Model
+Model weights can be loaded with Hugging Face Transformers. Examples can be found at [Github](https://github.com/Meituan-AutoML/MobileVLM).
+# Datasets and Training
+For our training details, please refer to our paper in section 4.1: [MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://arxiv.org/abs/2312.16886).