Downloads · 30 days
16
100% of all-time downloads
road-qwen25vl-lora-e1
ModarIbrahim/road-qwen25vl-lora-e1
road-qwen25vl-lora-e1 is a machine learning model from ModarIbrahim. 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.
LoRA adapter for line-level transcription of historic Barbados handwriting (Zindi R.O.A.D. challenge).
All-time downloads
16
Public
Repo size
415 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors415 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026
- SHA
- 5de02542
Base models
Model card
From the Hugging Face model README
R.O.A.D. Barbados Historic Handwriting — Qwen2.5-VL-7B LoRA
LoRA adapter for line-level transcription of historic Barbados handwriting (Zindi R.O.A.D. challenge).
- Base:
Qwen/Qwen2.5-VL-7B-Instruct - LoRA: r=32, alpha=64, dropout=0.05,
all-linear, bf16 - Trained only on competition data (no external OCR datasets)
- 2 epochs, image height 256, max_pixels 28282048
- Held-out val: WER 0.1551 / CER 0.0441 / score 0.9004; Zindi public LB 0.90413
Usage
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
from peft import PeftModel
import torch
base = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"Qwen/Qwen2.5-VL-7B-Instruct", dtype=torch.bfloat16).to("cuda")
model = PeftModel.from_pretrained(base, "ModarIbrahim/road-qwen25vl-lora").eval()
processor = AutoProcessor.from_pretrained(
"Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=256*28*28, max_pixels=28*28*2048)
processor.tokenizer.padding_side = "left"
- Library
- peft
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026