How to load model model that was finetuned using qlora or lora?

Tried finetuning using script/custom/finetune_qlora.sh but when i load the model using inference it was not working. How to load the model using the weight finetuned using qlora Tried this code
```
import sys
sys.path.append('./')
from videollama2 import model_init, mm_infer
from videollama2.utils import disable_torch_init

def inference():
disable_torch_init()

# Video Inference
modal = 'video'
modal_path = 'assets/cat_and_chicken.mp4'
instruct = 'What animals are in the video, what are they doing, and how does the video feel?'
# Reply:
# The video features a kitten and a baby chick playing together. The kitten is seen laying on the floor while the baby chick hops around. The two animals interact playfully with each other, and the video has a cute and heartwarming feel to it.

# Image Inference
modal = 'image'
modal_path = 'assets/sora.png'
instruct = 'What is the woman wearing, what is she doing, and how does the image feel?'
# Reply:
# The woman in the image is wearing a black coat and sunglasses, and she is walking down a rain-soaked city street. The image feels vibrant and lively, with the bright city lights reflecting off the wet pavement, creating a visually appealing atmosphere. The woman's presence adds a sense of style and confidence to the scene, as she navigates the bustling urban environment.

model_path = 'DAMO-NLP-SG/VideoLLaMA2.1-7B-16F'
# Base model inference (only need to replace model_path)
# model_path = 'DAMO-NLP-SG/VideoLLaMA2.1-7B-16F-Base'
model, processor, tokenizer = model_init(model_path)
output = mm_infer(processor[modal](modal_path), instruct, model=model, tokenizer=tokenizer, do_sample=False, modal=modal)

print(output)

if __name__ == "__main__":
inference()
```
Where I replaced the location of the model _path with the lora path but it was not working.Also i tried saving the full model by used merge and unload peft function but when i load the model and run the above script it was giving error that mat1 o size 1336x3564 cannot be multiplies with mat2 of size 512x3564

Start with script/custom/finetune_qlora.sh and the model_init call in the supplied inference example. Compare how the fine-tuned LoRA or merged model is saved with the path and model format expected by model_init, then rerun video or image inference; done means the weights load without the reported matrix-shape error and inference completes.

Written by the indexing model from the issue text.