Instructions to use bigscience/bloomz-7b1-p3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigscience/bloomz-7b1-p3 with Transformers:

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

pipe = pipeline("text-generation", model="bigscience/bloomz-7b1-p3")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-7b1-p3")
model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-7b1-p3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bigscience/bloomz-7b1-p3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigscience/bloomz-7b1-p3"
# 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-7b1-p3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bigscience/bloomz-7b1-p3

SGLang

How to use bigscience/bloomz-7b1-p3 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-7b1-p3" \
    --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-7b1-p3",
		"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-7b1-p3" \
        --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-7b1-p3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bigscience/bloomz-7b1-p3 with Docker Model Runner:
```
docker model run hf.co/bigscience/bloomz-7b1-p3
```

bloomz-7b1-p3

Commit History

Jan 20, 2025

14:28
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
a9cefba

Feb 10, 2023

16:34
Fix architecture (#1)⁠

cakiki +1: lewtun

c0b272f

Dec 3, 2022

12:35
Update README.md

Muennighoff

146ae0c

Nov 18, 2022

17:32
Update README.md

Muennighoff

91a55b4

Nov 4, 2022

00:47
Create README.md

Muennighoff

f5cbc1b

Oct 15, 2022

14:28
Add ru

Muennighoff

7f49339
14:24
Add res

Muennighoff

ad49413

Oct 9, 2022

12:42
Organize eval

Muennighoff

8634ce5

Sep 27, 2022

09:46
Add files

Muennighoff

1bcb202
09:43
initial commit

Muennighoff

0f2c63b

Commit History

Jan 20, 2025

Adding `safetensors` variant of this model⁠

Feb 10, 2023

Fix architecture (#1)⁠

Dec 3, 2022

Update README.md

Nov 18, 2022

Update README.md

Nov 4, 2022

Create README.md

Oct 15, 2022

Add ru

Add res

Oct 9, 2022

Organize eval

Sep 27, 2022

Add files

initial commit