Instructions to use alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2 with Transformers:

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

pipe = pipeline("text-generation", model="alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2")
model = AutoModelForCausalLM.from_pretrained("alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2

SGLang

How to use alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2 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 "alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2" \
    --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": "alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2",
		"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 "alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2" \
        --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": "alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2 with Docker Model Runner:
```
docker model run hf.co/alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2
```

Inference API works bad ???

by Trace2333 - opened Dec 15, 2023

Discussion

Trace2333

Dec 15, 2023

Inference API works very bad, and always generate repeat content.

jpWang

Alibaba-PAI org Dec 15, 2023

Hi,
what inference contents are you using?

Trace2333

Dec 20, 2023

my input in the Inference API: blue sky
It just returned: blue sky and the sun shining brightly in the sky.
input: Astronaut rides horse
returns: Astronaut rides horseback ride on moon in 1969 lunar eclipse. Photo: NASA
The 1969 lunar
I think it may not work properly.

Trace2333

Dec 20, 2023

my input in the Inference API: blue sky
It just returned: blue sky and the sun shining brightly in the sky.
input: Astronaut rides horse
returns: Astronaut rides horseback ride on moon in 1969 lunar eclipse. Photo: NASA
The 1969 lunar
I think it may not work properly.

The API i'm using is just the huggingface web Inference API. More detailly, alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2

jpWang

Alibaba-PAI org Dec 20, 2023

Hi,
you need to put your input "raw prompt" in here and use this entire paragraph as input to the model.

You can try this.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment