Downloads · 30 days
4
22% of all-time downloads
blip-vqa-chart-lora
Guibibo/blip-vqa-chart-lora
blip-vqa-chart-lora is a machine learning model from Guibibo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
This is a solo project. The model is a LoRA adapter for Salesforce/blip-vqa-base trained to answer questions about graphs.
All-time downloads
18
Public
Repo size
7.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.1 MB · 88%
At a glance
- Library
- peft
- Access
- Public
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025
- SHA
- dd2da3df
Base models
Model card
From the Hugging Face model README
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.
- Library
- peft
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025