Instructions to use bigscience/bloomz-1b1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigscience/bloomz-1b1 with Transformers:

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

pipe = pipeline("text-generation", model="bigscience/bloomz-1b1")

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

tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-1b1")
model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-1b1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bigscience/bloomz-1b1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigscience/bloomz-1b1"
# 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-1b1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bigscience/bloomz-1b1

SGLang

How to use bigscience/bloomz-1b1 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-1b1" \
    --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-1b1",
		"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-1b1" \
        --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-1b1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bigscience/bloomz-1b1 with Docker Model Runner:
```
docker model run hf.co/bigscience/bloomz-1b1
```

bloomz-1b1

Commit History

Mar 19, 2023

07:16
Adding `safetensors` variant of this model⁠

SFconvertbot

829b680

Feb 10, 2023

15:18
Fix architecture (#6)⁠

lewtun HF Staff

1618711
14:35
Fix architecture (#5)⁠

TimeRobber +1: lewtun

dcc9d8e

Dec 3, 2022

12:37
Update README.md

Muennighoff

cec189b

Nov 18, 2022

17:30
Update README.md

Muennighoff

1b30b5d

Nov 7, 2022

08:32
Remove eval folder (Moved to bigscience/evaluation-results)

Muennighoff

d6d5e6a

Nov 4, 2022

00:21
Add bibtex

Muennighoff

08b4421
00:13
Update README.md

Muennighoff

78a8ec4
00:10
Create README.md

Muennighoff

0ed61f2

Oct 9, 2022

12:00
Organize

Muennighoff

c4dca47
10:57
Add eval

Muennighoff

efac57d

Oct 8, 2022

19:40
Logs

Muennighoff

f7d5648
19:30
Add files

Muennighoff

d733d97
16:16
initial commit

Muennighoff

209130f

Commit History

Mar 19, 2023

Adding `safetensors` variant of this model⁠

Feb 10, 2023

Fix architecture (#6)⁠

Fix architecture (#5)⁠

Dec 3, 2022

Update README.md

Nov 18, 2022

Update README.md

Nov 7, 2022

Remove eval folder (Moved to bigscience/evaluation-results)

Nov 4, 2022

Add bibtex

Update README.md

Create README.md

Oct 9, 2022

Organize

Add eval

Oct 8, 2022

Logs

Add files

initial commit