Instructions to use bigscience/bloom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloom with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloom")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom") model = AutoModelForCausalLM.from_pretrained("bigscience/bloom") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use bigscience/bloom with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloom" # 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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloom
- SGLang
How to use bigscience/bloom 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" \ --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", "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" \ --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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloom with Docker Model Runner:
docker model run hf.co/bigscience/bloom
What is the length of the prompt considered by BLOOM?
See subject line. How long can a prompt be to be considered in its entirety? What happens if it exceeds some length, is the beginning cut off?
BLOOM was trained with sequences of length 2048, but uses ALiBi position embeddings (https://arxiv.org/abs/2108.12409) -- meaning it can be used with longer sequences.
So ALIBI allows input of what length to be considered? You write that it allows for “longer sequences” but this way I only know it is more than 2048…
Any update on this? @cakiki
I'd refer you to both the paper I linked to and empirical experimentation to answer that question. The practical limit will likely sooner be your hardware than any theoretical one.