Instructions to use Salesforce/blip2-opt-2.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/blip2-opt-2.7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Salesforce/blip2-opt-2.7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering

processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
model = AutoModelForVisualQuestionAnswering.from_pretrained("Salesforce/blip2-opt-2.7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/blip2-opt-2.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/blip2-opt-2.7b"
# 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-opt-2.7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/blip2-opt-2.7b

SGLang

How to use Salesforce/blip2-opt-2.7b 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-opt-2.7b" \
    --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-opt-2.7b",
		"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-opt-2.7b" \
        --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-opt-2.7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/blip2-opt-2.7b with Docker Model Runner:
```
docker model run hf.co/Salesforce/blip2-opt-2.7b
```

Blip and Blip2 comparison?

#22

by Johanderson - opened Dec 26, 2023

Discussion

Johanderson

Dec 26, 2023

There is any comparison between blip and blip2? how can I know which model should I prefer?

I haven't found any comparison on the web, maybe I'm a bad at searching?

I'm trying to get/extend descriptions from products based on it's images

Thanks!

nielsr

Dec 26, 2023

There's this Space which you can use to compare captioning performance: https://huggingface.co/spaces/nielsr/comparing-captioning-models

joancarles111

Jan 2, 2024

I think it is not working at the moment, it will be operational soon?

Thanks and sorry for the inconvenience! ;)

shams123321

Mar 14, 2024

There's this Space which you can use to compare captioning performance: https://huggingface.co/spaces/nielsr/comparing-captioning-models

This seems to be unusable at the moment.

userx1

Mar 23, 2025

•

edited Mar 23, 2025

There's this Space which you can use to compare captioning performance: https://huggingface.co/spaces/nielsr/comparing-captioning-models

warning
The BLIP-large Space is currently unavailable. Please try again later. ×
warning
The BLIP2 T5-XXL Space is currently unavailable. Please try again later.×
warning
The GIT-large Space is currently unavailable. Please try again later.×
warning
The Fuyu-8B Space is currently unavailable. Please try again later.×
warning
The BLIP2 OPT6.7B Space is currently unavailable. Please try again later.×
warning
The InstructBLIP Space is currently unavailable. Please try again later.

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