Image-Text-to-Text
PEFT
Safetensors
lora
document-ai
form-understanding
table-structure-recognition
synthetic-data
conversational
Instructions to use D2I-CUHK-Shenzhen/FormStruct-Bench-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use D2I-CUHK-Shenzhen/FormStruct-Bench-SFT with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B") model = PeftModel.from_pretrained(base_model, "D2I-CUHK-Shenzhen/FormStruct-Bench-SFT") - Notebooks
- Google Colab
- Kaggle
File size: 131 Bytes
51b5f42 | 1 2 3 4 5 6 | {
"fsdp_units_with_lora": 40,
"adapter_tensor_count": 380,
"save_mode": "per-unit FSDP full state dict; LoRA tensors only"
}
|