Instructions to use MetaIX/Alpaca-30B-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MetaIX/Alpaca-30B-Int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MetaIX/Alpaca-30B-Int4")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MetaIX/Alpaca-30B-Int4") model = AutoModelForCausalLM.from_pretrained("MetaIX/Alpaca-30B-Int4") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MetaIX/Alpaca-30B-Int4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MetaIX/Alpaca-30B-Int4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MetaIX/Alpaca-30B-Int4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MetaIX/Alpaca-30B-Int4
- SGLang
How to use MetaIX/Alpaca-30B-Int4 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 "MetaIX/Alpaca-30B-Int4" \ --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": "MetaIX/Alpaca-30B-Int4", "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 "MetaIX/Alpaca-30B-Int4" \ --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": "MetaIX/Alpaca-30B-Int4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MetaIX/Alpaca-30B-Int4 with Docker Model Runner:
docker model run hf.co/MetaIX/Alpaca-30B-Int4
Oobabooga Compatibility
#3
by Aedhix - opened
It seems that Oobabooga can't read .pt files, but the description of the model states that it can be used with Oobabooga. The server launcher itself refuses to parse .pt files as model files and instead searches for .bin files, I believe. I'm not sure if I'm doing something wrong or the description should be updated to omit references to Oobabooga or if there's supposed to be a .bin file in the files somewhere.