How to inference the model with lora?

[sterzhang]

RuntimeError: Error(s) in loading state_dict for LlavaLlamaForCausalLM:
size mismatch for model.mm_projector.0.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([2097152, 1]).
size mismatch for model.mm_projector.2.weight: copying a param with shape torch.Size([4096, 4096]) from checkpoint, the shape in current model is torch.Size([8388608, 1]).

Here is the error.

Below is my code:

import torch
from videollava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN
from videollava.conversation import conv_templates, SeparatorStyle
from videollava.model.builder import load_pretrained_model
from videollava.utils import disable_torch_init
from videollava.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria

def main():
    disable_torch_init()
    video = 'videollava/serve/examples/sample_demo_1.mp4'
    inp = 'Why is this video funny?'
    model_path = "./checkpoints/videollava-7b-lora_11_26"
    model_base = 'pretrained_weights/LanguageBind/Video-LLaVA-7B'
    cache_dir = 'cache_dir'
    device = 'cuda'
    load_4bit, load_8bit = True, False
    model_name = get_model_name_from_path(model_path)
    tokenizer, model, processor, _ = load_pretrained_model(model_path, model_base, model_name, load_8bit, load_4bit, device=device, cache_dir=cache_dir)

BTW, I am using finetune_lora.sh as my training script!

Do you know how to solve this issue? Many thanks!

[zhanchao019]

any solution? facing same issue