Instructions to use bigscience/bloom-7b1-petals with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigscience/bloom-7b1-petals with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bigscience/bloom-7b1-petals")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-7b1-petals")
model = AutoModelForCausalLM.from_pretrained("bigscience/bloom-7b1-petals")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bigscience/bloom-7b1-petals with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigscience/bloom-7b1-petals"
# 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-7b1-petals",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bigscience/bloom-7b1-petals

SGLang

How to use bigscience/bloom-7b1-petals 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-7b1-petals" \
    --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-7b1-petals",
		"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-7b1-petals" \
        --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-7b1-petals",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bigscience/bloom-7b1-petals with Docker Model Runner:
```
docker model run hf.co/bigscience/bloom-7b1-petals
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

BLOOM, a version for Petals

This model is a version of bigscience/bloom-7b1 post-processed to be run at home using the Petals swarm.

Note: Petals is developed to run 100B+ models like the full-scale BLOOM or BLOOMZ. This model is provided for testing purposes only. It may be more efficient to run the original version of it locally.

Please check out:

The original model card to learn about the model's capabilities, specifications, and terms of use.
The Petals repository to learn how to install Petals and run this model over the Petals swarm.

We provide minimal code examples below.

Using the model

from petals import DistributedBloomForCausalLM

model = DistributedBloomForCausalLM.from_pretrained("bigscience/bloom-7b1-petals")
# Embeddings & prompts are on your device, BLOOM blocks are distributed across the Internet

inputs = tokenizer("A cat sat", return_tensors="pt")["input_ids"]
outputs = model.generate(inputs, max_new_tokens=5)
print(tokenizer.decode(outputs[0]))  # A cat sat on a mat...

Serving the model blocks

python -m petals.cli.run_server bigscience/bloom-7b1-petals

Downloads last month: 1,147

Safetensors

Model size

1B params

Tensor type

F16

bigscience
/

bloom-7b1-petals

BLOOM, a version for Petals

Using the model

Serving the model blocks

Spaces using bigscience/bloom-7b1-petals 9