metadata
license: apache-2.0
tags:
- vision
- blip-2
- vqa
- lora
My Fine-Tuned BLIP-2 Model
Custom BLIP-2 model fine-tuned for visual question answering with LoRA adapters
Usage
from transformers import Blip2ForConditionalGeneration, Blip2Processor
import torch
model = Blip2ForConditionalGeneration.from_pretrained(
"Magneto76/lora_blip2",
torch_dtype=torch.float16,
device_map="auto"
)
processor = Blip2Processor.from_pretrained("Magneto76/lora_blip2")
def infer(image, question):
inputs = processor(image, question, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs)
return processor.decode(outputs[0], skip_special_tokens=True)