Blip2 Flan Lora Finetuned Six Epoch

🚀 Model Card for Model ID

This model card provides an overview of a transformers model. It details the model's information, usage, training, evaluation, and more.

📚 Documentation

Model Details

Model Description

This is the model card of a 🤖 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

This code demonstrates how to use the fine-tuned BLIP - 2 model with LoRA adapters to generate chest X - ray reports from medical images. It loads the base BLIP - 2 model, applies the LoRA weights from this repository, and performs inference on an uploaded image in a Colab environment.

from PIL import Image
from IPython.display import display
import torch
from transformers import Blip2Processor, Blip2ForConditionalGeneration
from google.colab import files
from peft import PeftModel

# Upload image
uploaded = files.upload()
image_path = list(uploaded.keys())[0]

# Display image
image = Image.open(image_path).convert("RGB")
display(image)

# Load processor and model
model_id = "efeozdilek/blip2-flan-lora-finetuned-six-epoch"
processor = Blip2Processor.from_pretrained(model_id)

# Load base BLIP-2 and apply LoRA weights
base_model = Blip2ForConditionalGeneration.from_pretrained(
    "Salesforce/blip2-flan-t5-xl",
    device_map="auto",
    torch_dtype=torch.float16
)
model = PeftModel.from_pretrained(base_model, model_id)

# Preprocess input
inputs = processor(images=image, return_tensors="pt")
inputs = {k: v.to(model.device, dtype=torch.float32) for k, v in inputs.items()}

# Generate report
model.eval()
with torch.no_grad():
    generated_ids = model.generate(**inputs, max_new_tokens=256)
    report = processor.tokenizer.decode(generated_ids[0], skip_special_tokens=True)

print("\n📋 Generated Report:\n", report)

Bias, Risks, and Limitations

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Training Details

Training Data

[More Information Needed]

Training Procedure

Training Hyperparameters

• Training regime: [More Information Needed]

Evaluation

Testing Data, Factors & Metrics

• Testing Data: [More Information Needed]
• Factors: [More Information Needed]
• Metrics: [More Information Needed]

Results

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).