FormStruct-Bench-SFT

FormStruct-Bench-SFT is a PEFT LoRA adapter for Qwen/Qwen3.6-35B-A3B. It is fine-tuned on synthetic FormStruct training data for structured form understanding from document images.

Loading

import torch
from peft import PeftModel
from transformers import AutoModelForImageTextToText, AutoProcessor

base_id = "Qwen/Qwen3.6-35B-A3B"
adapter_id = "D2I-CUHK-Shenzhen/FormStruct-Bench-SFT"

processor = AutoProcessor.from_pretrained(adapter_id, trust_remote_code=True)
base_model = AutoModelForImageTextToText.from_pretrained(
    base_id,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

License

Apache-2.0, following the base model license. See LICENSE.

Downloads last month: 21

Model tree for D2I-CUHK-Shenzhen/FormStruct-Bench-SFT

Base model

Qwen/Qwen3.6-35B-A3B

Adapter

(223)

this model

Collection including D2I-CUHK-Shenzhen/FormStruct-Bench-SFT

FormStruct-Bench-SFT

Collection

LoRA adapters fine-tuned on synthetic FormStruct-Bench data for structured form understanding. • 2 items • Updated 6 days ago