Instructions to use Salesforce/blip2-flan-t5-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/blip2-flan-t5-xl with Transformers:

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

pipe = pipeline("image-text-to-text", model="Salesforce/blip2-flan-t5-xl")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Salesforce/blip2-flan-t5-xl")
model = AutoModelForMultimodalLM.from_pretrained("Salesforce/blip2-flan-t5-xl", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Salesforce/blip2-flan-t5-xl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/blip2-flan-t5-xl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/blip2-flan-t5-xl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/blip2-flan-t5-xl

SGLang

How to use Salesforce/blip2-flan-t5-xl 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 "Salesforce/blip2-flan-t5-xl" \
    --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": "Salesforce/blip2-flan-t5-xl",
		"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 "Salesforce/blip2-flan-t5-xl" \
        --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": "Salesforce/blip2-flan-t5-xl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/blip2-flan-t5-xl with Docker Model Runner:
```
docker model run hf.co/Salesforce/blip2-flan-t5-xl
```

Inference Error: Expected all tensors to be on the same device, but found at least two devices, cuda:7 and cuda:2!

by LDY - opened Oct 14, 2023

Discussion

LDY

Oct 14, 2023

I find RuntimeError when I use the official code on inference:

Expected all tensors to be on the same device, but found at least two devices, cuda:7 and cuda:2!

Test code:

model_path = ".cache/huggingface/hub/models--Salesforce--blip2-flan-t5-xl/snapshots/cc2bb7bce2f7d4d1c37753c7e9c05a443a226614/"
processor = Blip2Processor.from_pretrained(model_path)
model = Blip2ForConditionalGeneration.from_pretrained(model_path, device_map="auto")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

question = "how many dogs are in the picture?"
inputs = processor(raw_image, question, return_tensors="pt").to("cuda")

print("model: ",model.hf_device_map)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

System Info:

OS: 18.04.2 LTS
One mechine with 8x tesla p100-pcie-16gb

How can I fix this bug?

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