Inference code does not work for videos

[marvlyngkhoi]

The inference code provided does not work

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.


    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()

following error occur

[LiangMeng89]

I also get this problem by using the old inference code. Image inference is OK,but video inference don't work, please help me to solve this issue.

1. My inference code:
   import torch
   import transformers

import sys
sys.path.append('./')
from videollama2.conversation import conv_templates
from videollama2.constants import DEFAULT_MMODAL_TOKEN, MMODAL_TOKEN_INDEX
from videollama2.mm_utils import get_model_name_from_path, tokenizer_MMODAL_token, process_video, process_image
from videollama2.model.builder import load_pretrained_model

def inference():
# Video Inference
paths = ['assets/cat_and_chicken.mp4']
questions = ['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.
modal_list = ['video']

# Image Inference
paths = ['assets/sora.png']
questions = ['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.
modal_list = ['image']

# 1. Initialize the model.
model_path = './checkpoints/VideoLLaMA2-7B'   # DAMO-NLP-SG/VideoLLaMA2-7B
# Base model inference (only need to replace model_path)
# model_path = 'DAMO-NLP-SG/VideoLLaMA2-7B-Base'
model_name = get_model_name_from_path(model_path)
tokenizer, model, processor, context_len = load_pretrained_model(model_path, None, model_name)
model = model.to('cuda:0')
conv_mode = 'llama2'

# 2. Visual preprocess (load & transform image or video).
if modal_list[0] == 'video':
    tensor = process_video(paths[0], processor, model.config.image_aspect_ratio).to(dtype=torch.float16, device='cuda', non_blocking=True)
    default_mm_token = DEFAULT_MMODAL_TOKEN["VIDEO"]
    modal_token_index = MMODAL_TOKEN_INDEX["VIDEO"]
else:
    tensor = process_image(paths[0], processor, model.config.image_aspect_ratio)[0].to(dtype=torch.float16, device='cuda', non_blocking=True)
    default_mm_token = DEFAULT_MMODAL_TOKEN["IMAGE"]
    modal_token_index = MMODAL_TOKEN_INDEX["IMAGE"]
tensor = [tensor]

# 3. text preprocess (tag process & generate prompt).
question = default_mm_token + "\n" + questions[0]
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_MMODAL_token(prompt, tokenizer, modal_token_index, return_tensors='pt').unsqueeze(0).to('cuda:0')

with torch.inference_mode():
    output_ids = model.generate(
        input_ids,
        images_or_videos=tensor,
        modal_list=modal_list,
        do_sample=True,
        temperature=0.2,
        max_new_tokens=1024,
        use_cache=True,
    )

outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
print(outputs[0])

if name == "main":
inference()

2.Terminal show:
(videollama2) (base) lm@SR6430G23:~/videollama2/VideoLLaMA2$ python inference.py
200
2024-10-29 00:03:33.555533: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE4.1 SSE4.2 AVX AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
You are using a model of type videollama2_mistral to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 4/4 [00:05<00:00, 1.37s/it]
Some weights of the model checkpoint at ./checkpoints/VideoLLaMA2-7B were not used when initializing Videollama2MistralForCausalLM: ['model.vision_tower.vision_tower.vision_model.embeddings.class_embedding', 'model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight', 'model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.post_layernorm.bias', 'model.vision_tower.vision_tower.vision_model.post_layernorm.weight', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight']

• This IS expected if you are initializing Videollama2MistralForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing Videollama2MistralForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results.
  Setting pad_token_id to eos_token_id:2 for open-end generation.
  The woman is wearing a black coat and sunglasses, and she is walking down a busy city street at night. The image feels vibrant and lively, with the bright lights and neon signs illuminating the scene. The woman appears confident and stylish as she navigates the bustling urban environment.

[LiangMeng89]

I also get this problem by using the old inference code. Image inference is OK,but video inference don't work, please help me to solve this issue.

1. My inference code:
   import torch
   import transformers

import sys sys.path.append('./') from videollama2.conversation import conv_templates from videollama2.constants import DEFAULT_MMODAL_TOKEN, MMODAL_TOKEN_INDEX from videollama2.mm_utils import get_model_name_from_path, tokenizer_MMODAL_token, process_video, process_image from videollama2.model.builder import load_pretrained_model

def inference(): # Video Inference paths = ['assets/cat_and_chicken.mp4'] questions = ['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. modal_list = ['video']

# Image Inference
paths = ['assets/sora.png']
questions = ['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.
modal_list = ['image']

# 1. Initialize the model.
model_path = './checkpoints/VideoLLaMA2-7B'   # DAMO-NLP-SG/VideoLLaMA2-7B
# Base model inference (only need to replace model_path)
# model_path = 'DAMO-NLP-SG/VideoLLaMA2-7B-Base'
model_name = get_model_name_from_path(model_path)
tokenizer, model, processor, context_len = load_pretrained_model(model_path, None, model_name)
model = model.to('cuda:0')
conv_mode = 'llama2'

# 2. Visual preprocess (load & transform image or video).
if modal_list[0] == 'video':
    tensor = process_video(paths[0], processor, model.config.image_aspect_ratio).to(dtype=torch.float16, device='cuda', non_blocking=True)
    default_mm_token = DEFAULT_MMODAL_TOKEN["VIDEO"]
    modal_token_index = MMODAL_TOKEN_INDEX["VIDEO"]
else:
    tensor = process_image(paths[0], processor, model.config.image_aspect_ratio)[0].to(dtype=torch.float16, device='cuda', non_blocking=True)
    default_mm_token = DEFAULT_MMODAL_TOKEN["IMAGE"]
    modal_token_index = MMODAL_TOKEN_INDEX["IMAGE"]
tensor = [tensor]

# 3. text preprocess (tag process & generate prompt).
question = default_mm_token + "\n" + questions[0]
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_MMODAL_token(prompt, tokenizer, modal_token_index, return_tensors='pt').unsqueeze(0).to('cuda:0')

with torch.inference_mode():
    output_ids = model.generate(
        input_ids,
        images_or_videos=tensor,
        modal_list=modal_list,
        do_sample=True,
        temperature=0.2,
        max_new_tokens=1024,
        use_cache=True,
    )

outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
print(outputs[0])

if name == "main": inference()

2.Terminal show: (videollama2) (base) lm@SR6430G23:~/videollama2/VideoLLaMA2$ python inference.py 200 2024-10-29 00:03:33.555533: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: SSE4.1 SSE4.2 AVX AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. You are using a model of type videollama2_mistral to instantiate a model of type . This is not supported for all configurations of models and can yield errors. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 4/4 [00:05<00:00, 1.37s/it] Some weights of the model checkpoint at ./checkpoints/VideoLLaMA2-7B were not used when initializing Videollama2MistralForCausalLM: ['model.vision_tower.vision_tower.vision_model.embeddings.class_embedding', 'model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight', 'model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.post_layernorm.bias', 'model.vision_tower.vision_tower.vision_model.post_layernorm.weight', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight']

* This IS expected if you are initializing Videollama2MistralForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).

* This IS NOT expected if you are initializing Videollama2MistralForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
  Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.
  The woman is wearing a black coat and sunglasses, and she is walking down a busy city street at night. The image feels vibrant and lively, with the bright lights and neon signs illuminating the scene. The woman appears confident and stylish as she navigates the bustling urban environment.

First,I used my qlore checkpoints to do the video inference,it didn't work, then I came back to use the orignal code and data which you show in the README file.

[LiangMeng89]

I also get this problem by using the old inference code. Image inference is OK,but video inference don't work, please help me to solve this issue.

1. My inference code:
   import torch
   import transformers

import sys sys.path.append('./') from videollama2.conversation import conv_templates from videollama2.constants import DEFAULT_MMODAL_TOKEN, MMODAL_TOKEN_INDEX from videollama2.mm_utils import get_model_name_from_path, tokenizer_MMODAL_token, process_video, process_image from videollama2.model.builder import load_pretrained_model
def inference(): # Video Inference paths = ['assets/cat_and_chicken.mp4'] questions = ['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. modal_list = ['video']

# Image Inference
paths = ['assets/sora.png']
questions = ['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.
modal_list = ['image']

# 1. Initialize the model.
model_path = './checkpoints/VideoLLaMA2-7B'   # DAMO-NLP-SG/VideoLLaMA2-7B
# Base model inference (only need to replace model_path)
# model_path = 'DAMO-NLP-SG/VideoLLaMA2-7B-Base'
model_name = get_model_name_from_path(model_path)
tokenizer, model, processor, context_len = load_pretrained_model(model_path, None, model_name)
model = model.to('cuda:0')
conv_mode = 'llama2'

# 2. Visual preprocess (load & transform image or video).
if modal_list[0] == 'video':
    tensor = process_video(paths[0], processor, model.config.image_aspect_ratio).to(dtype=torch.float16, device='cuda', non_blocking=True)
    default_mm_token = DEFAULT_MMODAL_TOKEN["VIDEO"]
    modal_token_index = MMODAL_TOKEN_INDEX["VIDEO"]
else:
    tensor = process_image(paths[0], processor, model.config.image_aspect_ratio)[0].to(dtype=torch.float16, device='cuda', non_blocking=True)
    default_mm_token = DEFAULT_MMODAL_TOKEN["IMAGE"]
    modal_token_index = MMODAL_TOKEN_INDEX["IMAGE"]
tensor = [tensor]

# 3. text preprocess (tag process & generate prompt).
question = default_mm_token + "\n" + questions[0]
conv = conv_templates[conv_mode].copy()
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_MMODAL_token(prompt, tokenizer, modal_token_index, return_tensors='pt').unsqueeze(0).to('cuda:0')

with torch.inference_mode():
    output_ids = model.generate(
        input_ids,
        images_or_videos=tensor,
        modal_list=modal_list,
        do_sample=True,
        temperature=0.2,
        max_new_tokens=1024,
        use_cache=True,
    )

outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
print(outputs[0])

if name == "main": inference()
2.Terminal show: (videollama2) (base) lm@SR6430G23:~/videollama2/VideoLLaMA2$ python inference.py 200 2024-10-29 00:03:33.555533: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: SSE4.1 SSE4.2 AVX AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. You are using a model of type videollama2_mistral to instantiate a model of type . This is not supported for all configurations of models and can yield errors. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 4/4 [00:05<00:00, 1.37s/it] Some weights of the model checkpoint at ./checkpoints/VideoLLaMA2-7B were not used when initializing Videollama2MistralForCausalLM: ['model.vision_tower.vision_tower.vision_model.embeddings.class_embedding', 'model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight', 'model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias', 'model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight', 'model.vision_tower.vision_tower.vision_model.post_layernorm.bias', 'model.vision_tower.vision_tower.vision_model.post_layernorm.weight', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias', 'model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight']

* This IS expected if you are initializing Videollama2MistralForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).

* This IS NOT expected if you are initializing Videollama2MistralForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
  Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.
  The woman is wearing a black coat and sunglasses, and she is walking down a busy city street at night. The image feels vibrant and lively, with the bright lights and neon signs illuminating the scene. The woman appears confident and stylish as she navigates the bustling urban environment.

First,I used my qlore checkpoints to do the video inference,it didn't work, then I came back to use the orignal code and data which you show in the README file.

It's working now,but using my data's qlore checkpoints to inference new test video data is don't work.