Instructions to use Salesforce/instructblip-vicuna-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/instructblip-vicuna-13b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Salesforce/instructblip-vicuna-13b")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Salesforce/instructblip-vicuna-13b")
model = AutoModelForImageTextToText.from_pretrained("Salesforce/instructblip-vicuna-13b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/instructblip-vicuna-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/instructblip-vicuna-13b"
# 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-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/instructblip-vicuna-13b

SGLang

How to use Salesforce/instructblip-vicuna-13b 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-13b" \
    --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-13b",
		"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-13b" \
        --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-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/instructblip-vicuna-13b with Docker Model Runner:
```
docker model run hf.co/Salesforce/instructblip-vicuna-13b
```

How could we load the model with low gpu memory?

by erjiaxiao - opened Apr 16, 2024

Discussion

erjiaxiao

Apr 16, 2024

My GPU memory is 24GB, which is not enough for the model. How could we load the model with low GPU memory?

nielsr

Apr 16, 2024

•

edited Apr 16, 2024

Hi,

You can pass a quantization_config to the from_pretrained method in order for it to load in fewer bytes (like 4 bit or 8 bit):

from transformers import BitsAndBytesConfig, InstructBlipForConditionalGeneration

quantization_config = BitsAndBytesConfig(load_in_4bit=True)

model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-13b", device_map="auto", quantization_config=quantization_config)

Refer to the blog post for details: https://huggingface.co/blog/4bit-transformers-bitsandbytes

erjiaxiao

Apr 16, 2024

Thank you so much for your help!

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