Instructions to use Salesforce/instructblip-vicuna-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/instructblip-vicuna-7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Salesforce/instructblip-vicuna-7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b")
model = AutoModelForImageTextToText.from_pretrained("Salesforce/instructblip-vicuna-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/instructblip-vicuna-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/instructblip-vicuna-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/instructblip-vicuna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/instructblip-vicuna-7b

SGLang

How to use Salesforce/instructblip-vicuna-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/instructblip-vicuna-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/instructblip-vicuna-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/instructblip-vicuna-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/instructblip-vicuna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/instructblip-vicuna-7b with Docker Model Runner:
```
docker model run hf.co/Salesforce/instructblip-vicuna-7b
```

Model gets stuck in a hallucinating loop

by PeePants - opened Aug 15, 2023

Discussion

PeePants

Aug 15, 2023

The results are mostly amazing and InstructBlip is clearly much better than other alternatives. However, I'm finding the Vicuna version will just kinda freak out sometimes, even with a very simple prompt, and will get itself in a loop that fills up all the gpu memory. There doesn't appear to be any options that will help stop it. Do you have any idea how to make this more stable? are there other models that could be adapted to work with Blip like this? The wizard models are quite good as well. Any thoughts would be really appreciated.

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