Configuration Parsing Warning: In adapter_config.json: "peft.task_type" must be a string
LoRA Adapter – Personal Project
This is a solo project.
The model is a LoRA adapter for Salesforce/blip-vqa-base trained to answer questions about graphs.
⚠️ Warning: This model is experimental and does not perform well. Use only for testing or personal experiments.
Usage
from transformers import AutoModelForVisionQuestionAnswering, AutoProcessor from peft import PeftModel
Load base model
base_model = AutoModelForVisionQuestionAnswering.from_pretrained("Salesforce/blip-vqa-base")
Load processor
processor = AutoProcessor.from_pretrained("USERNAME/YOUR_LORA_ADAPTER")
Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "USERNAME/YOUR_LORA_ADAPTER")
License
This project is released under the MIT License — use freely.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Guibibo/blip-vqa-chart-lora
Base model
Salesforce/blip-vqa-base