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
Adding `safetensors` variant of this model
Converted from this Space: https://huggingface.co/spaces/safetensors/convert
Maybe it'd be better to have the safetensors variant on a different branch, so cloning doesn't take longer?
The only benefit of this is that it's safer right? I.e. in this case where we know it's safe there is no benefit, no?
so cloning doesn't take longer?
not many people git clone those repos though, no? (vs. programmatic access via huggingface_hub or other libraries)
The only benefit of this is that it's safer right? I.e. in this case where we know it's safe there is no benefit, no?
It has the benefit of enabling cool features on the hub like knowing the number of params in a model :)
not many people git clone those repos though, no? (vs. programmatic access via huggingface_hub or other libraries)
I do quite often to update things & unfortunately you can't ignore files w/ git clone :(
It has the benefit of enabling cool features on the hub like knowing the number of params in a model :)
Oh okay nice, I didn't know about those!
Anyways I guess it's fine. I can't test it unfortunately, but if you tested it & works, we can merge from my side!
It's also much faster to load in upcoming release.
It was used by @olivierdehaene to deploy bloomz for example. Btw the text is wrong, I used a custom script for it. Let's merge for now, if you have issues with it we can always remove vut right now I'd say that deployment is more important.