Instructions to use bigscience/bloomz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloomz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloomz")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz") model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigscience/bloomz with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloomz" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigscience/bloomz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloomz
- SGLang
How to use bigscience/bloomz 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/bloomz" \ --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/bloomz", "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/bloomz" \ --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/bloomz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloomz with Docker Model Runner:
docker model run hf.co/bigscience/bloomz
Repetitive Output
I have been playing around with the mt0 models and smaller bloomz models. Currently I am running bloomz-1b1 and my output gets really repetitive. Is there any way to fix this other than post-processing the text to cut out duplicate text?
Example input (I took prompt suggestion from the docs):
Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
Output:
A un troll le gustaba mucho la vida. Él era un hombre muy feliz. Él tenía un gran jardín y una hermosa princesa. Él tenía un gran jardín y una hermosa princesa. Él tenía un gran jardín y una hermosa princesa. Él tenía un gran jardín y una hermosa princesa. Él tenía un gran jardín y una hermosa princesa. Él tenía un gran jardín y una hermosa princesa.
As you can see, the last sentence keeps repeating as much as the max_length i set allows. This happens with other prompts too. Any advice?
Yes you can increase temperature; Maybe you're doing greedy atm