Instructions to use bigscience/bloom-560m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloom-560m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloom-560m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-560m") model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-560m") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bigscience/bloom-560m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloom-560m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigscience/bloom-560m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloom-560m
- SGLang
How to use bigscience/bloom-560m 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 "bigscience/bloom-560m" \ --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": "bigscience/bloom-560m", "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 "bigscience/bloom-560m" \ --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": "bigscience/bloom-560m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloom-560m with Docker Model Runner:
docker model run hf.co/bigscience/bloom-560m
Is this model still being used in production?
Dear Team,
Thanks a lot for the amazing work on Bloom. I still look back often on all those exciting days!
As part of our ongoing efforts to keep the vLLM codebase clean and maintainable, we are currently reviewing older architectures to see if they are still actively used. We wanted to check in with you to see what the current usage looks like for Bloom.
If it's no longer used by vLLM users, we are considering removing the implementation from vLLM and transitioning it to the Transformers fallback. This way, the model can still remain fully functional for anyone who needs it, while allowing us to streamline the core repository.
We'd love to get your thoughts and alignment on this. Let us know what you think!
Best regards,
Tiezhen