Instructions to use MBZUAI/MobiLlama-08B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/MobiLlama-08B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MBZUAI/MobiLlama-08B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MBZUAI/MobiLlama-08B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("MBZUAI/MobiLlama-08B", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MBZUAI/MobiLlama-08B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/MobiLlama-08B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/MobiLlama-08B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/MobiLlama-08B
- SGLang
How to use MBZUAI/MobiLlama-08B 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 "MBZUAI/MobiLlama-08B" \ --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": "MBZUAI/MobiLlama-08B", "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 "MBZUAI/MobiLlama-08B" \ --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": "MBZUAI/MobiLlama-08B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/MobiLlama-08B with Docker Model Runner:
docker model run hf.co/MBZUAI/MobiLlama-08B
Commit History
Update config.json 29be8bf verified
Rename modeling_mobillama.py to modelling_mobillama.py 1369f11 verified
Update README.md 20b2991 verified
Upload MobileLLaMa.png f09f1db verified
initial upload 9f44f8d verified
initial upload 4682654 verified
Omkar Thawakar commited on
initial upload 654a234 verified
Omkar Thawakar commited on
initial upload 9a0631c verified
Omkar Thawakar commited on
initial commit a5fce5b verified
Omkar Thawakar commited on