Instructions to use Mediocreatmybest/instructblip-vicuna-13b_8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mediocreatmybest/instructblip-vicuna-13b_8bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mediocreatmybest/instructblip-vicuna-13b_8bit")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Mediocreatmybest/instructblip-vicuna-13b_8bit")
model = AutoModelForMultimodalLM.from_pretrained("Mediocreatmybest/instructblip-vicuna-13b_8bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mediocreatmybest/instructblip-vicuna-13b_8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mediocreatmybest/instructblip-vicuna-13b_8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mediocreatmybest/instructblip-vicuna-13b_8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mediocreatmybest/instructblip-vicuna-13b_8bit

SGLang

How to use Mediocreatmybest/instructblip-vicuna-13b_8bit 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 "Mediocreatmybest/instructblip-vicuna-13b_8bit" \
    --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": "Mediocreatmybest/instructblip-vicuna-13b_8bit",
		"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 "Mediocreatmybest/instructblip-vicuna-13b_8bit" \
        --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": "Mediocreatmybest/instructblip-vicuna-13b_8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mediocreatmybest/instructblip-vicuna-13b_8bit with Docker Model Runner:
```
docker model run hf.co/Mediocreatmybest/instructblip-vicuna-13b_8bit
```

Input type (float) and bias type (struct c10::Half) should be the same

by manzonif - opened Aug 6, 2023

Discussion

manzonif

Aug 6, 2023

Hi, I'm trying to use your quantized version but i'm stuck on the following error.
"Input type (float) and bias type (struct c10::Half) should be the same"
In "outputs = model.generate("

I guess some kind of normalization is needed. can you help me? This is my code:
from transformers import InstructBlipProcessor, InstructBlipForConditionalGeneration
import torch
from PIL import Image
import requests

model = InstructBlipForConditionalGeneration.from_pretrained("Mediocreatmybest/instructblip-vicuna-13b_8bit")
processor = InstructBlipProcessor.from_pretrained("Mediocreatmybest/instructblip-vicuna-13b_8bit")

device = "cuda" if torch.cuda.is_available() else "cpu"

url = "https://raw.githubusercontent.com/salesforce/LAVIS/main/docs/_static/Confusing-Pictures.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
prompt = "What is unusual about this image?"
inputs = processor(images=image, text=prompt, return_tensors="pt").to(device)

outputs = model.generate(
**inputs,
do_sample=False,
num_beams=5,
max_length=256,
min_length=1,
top_p=0.9,
repetition_penalty=1.5,
length_penalty=1.0,
temperature=1,
)
generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip()
print(generated_text)