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
- 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
BloomTokenizerFast does not exist
I tried out the model but got the error:
Tokenizer class BloomTokenizerFast does not exist or is not currently imported.
What should I do?
I am kinda new to python so this might be some beginner problem.
Hi @hiddenchamp
Thanks for your message!
I suspect you are using an old version of transformers - can you try:
import transformers
print(transformers.__version__)
You probably want to upgrade the library by running pip install --upgrade transformers
I did upgrade it. My version is 4.19.2
What should I do now?
I also tried bloomz and I get the same error.
Thanks for trying to help. I have nobody else to ask :(
Latest version should be https://github.com/huggingface/transformers/releases/tag/v4.25.1 . I'm not sure why it didn't update itself?
Hi @hiddenchamp
Can you try to uninstall transformers and re-install it again? And alternatively upgrade pip as well pip install --upgrade pip
Same error still on transformers-4.30.0.dev0
│ 692 │ │ │ │ ) │
│ 693 │ │ │ return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *input │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: Tokenizer class BloomTokenizer does not exis
@cakiki sorry im in the wrong place