Instructions to use bigscience/bloom-1b7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloom-1b7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloom-1b7")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-1b7") model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-1b7") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigscience/bloom-1b7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloom-1b7" # 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-1b7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloom-1b7
- SGLang
How to use bigscience/bloom-1b7 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-1b7" \ --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-1b7", "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-1b7" \ --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-1b7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloom-1b7 with Docker Model Runner:
docker model run hf.co/bigscience/bloom-1b7
KeyError: "bloom"
Currently, I think the transformers library hasn't support the bloom model. Our multilingual modeling group is starting to finetune it on new languages, so I wonder if there's any resource/pointer to adding model support into transformers.
I did a quick run through the HF's documentation but couldn't find any, and before I start looking at GitHub commits, I decide to post the question here.
>>> model = transformers.AutoModel.from_pretrained("bigscience/bloom-1b3", cache_dir="/users/zyong2/data/zyong2/huggingface/", use_auth_token=True)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/gpfs/data/sbach/zyong2/bigscience/env_lang_adapter/lib/python3.7/site-packages/transformers/models/auto/auto_factory.py", line 425, in from_pretrained
pretrained_model_name_or_path, return_unused_kwargs=True, trust_remote_code=trust_remote_code, **kwargs
File "/gpfs/data/sbach/zyong2/bigscience/env_lang_adapter/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 657, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/gpfs/data/sbach/zyong2/bigscience/env_lang_adapter/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 372, in __getitem__
raise KeyError(key)
KeyError: 'bloom'
The BLOOM class is not yet merged into main. You'll have to checkout this PR: https://github.com/huggingface/transformers/pull/17202
Sorry, this PR: https://github.com/huggingface/transformers/pull/17474 (The previous one was moved into this one)
Gotcha! I am reading through the PR right now.