How to modify the vision encoder of llava-llama3-8b?

[Jason8Kang]

I'd like to replace the vision encoder of vit (openai/clip-vit-large-patch14-336) with swin-transformers v2(microsoft/swinv2-base-patch4-window8-256)
I modify the code in config file. I replace 'from transformers import CLIPImageProcessor, CLIPVisionModel' with 'from transformers import (AutoImageProcessor, Swinv2Model)'. This is the whole config file.

`from mmengine.dataset import DefaultSampler
from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
LoggerHook, ParamSchedulerHook)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR
from torch.optim import AdamW
from transformers import (AutoModelForCausalLM, AutoTokenizer, AutoImageProcessor, Swinv2Model)

from xtuner.dataset import LLaVADataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import llava_map_fn, template_map_fn_factory
from xtuner.engine.hooks import DatasetInfoHook, EvaluateChatHook
from xtuner.engine.runner import TrainLoop
from xtuner.model import LLaVAModel
from xtuner.utils import PROMPT_TEMPLATE

#######################################################################

PART 1 Settings

#######################################################################

Model

llm_name_or_path = 'meta-llama/Meta-Llama-3-8B-Instruct'
visual_encoder_name_or_path = 'openai/clip-vit-large-patch14-336'

Data

data_root = ''
data_path = data_root + ''
image_folder = data_root
prompt_template = PROMPT_TEMPLATE.llama3_chat
max_length = 512

Scheduler & Optimizer

batch_size = 2 # per_device
accumulative_counts = 2
dataloader_num_workers = 4
max_epochs = 1
optim_type = AdamW
lr = 1e-3
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1 # grad clip
warmup_ratio = 0.03

Save

save_steps = 1000
save_total_limit = 2 # Maximum checkpoints to keep (-1 means unlimited)

Evaluate the generation performance during the training

evaluation_freq = 1000
SYSTEM = ''
evaluation_images = '**'
evaluation_inputs = ["please review this table image and return a text representation of the table in HTML format."]

#######################################################################

PART 2 Model & Tokenizer & Image Processor

#######################################################################
tokenizer = dict(
type=AutoTokenizer.from_pretrained,
pretrained_model_name_or_path=llm_name_or_path,
trust_remote_code=True,
padding_side='right')

image_processor = dict(
type=AutoImageProcessor.from_pretrained,
pretrained_model_name_or_path=visual_encoder_name_or_path,
trust_remote_code=True)

model = dict(
type=LLaVAModel,
freeze_llm=True,
freeze_visual_encoder=True,
llm=dict(
type=AutoModelForCausalLM.from_pretrained,
pretrained_model_name_or_path=llm_name_or_path,
trust_remote_code=True),
visual_encoder=dict(
type=Swinv2Model.from_pretrained,
pretrained_model_name_or_path=visual_encoder_name_or_path))

#######################################################################

PART 3 Dataset & Dataloader

#######################################################################
llava_dataset = dict(
type=LLaVADataset,
data_path=data_path,
image_folder=image_folder,
tokenizer=tokenizer,
image_processor=image_processor,
dataset_map_fn=llava_map_fn,
template_map_fn=dict(
type=template_map_fn_factory, template=prompt_template),
max_length=max_length,
pad_image_to_square=False)

train_dataloader = dict(
batch_size=batch_size,
num_workers=dataloader_num_workers,
pin_memory=True,
dataset=llava_dataset,
sampler=dict(type=DefaultSampler, shuffle=True),
collate_fn=dict(type=default_collate_fn))

#######################################################################

PART 4 Scheduler & Optimizer

#######################################################################

optimizer

optim_wrapper = dict(
type=AmpOptimWrapper,
optimizer=dict(
type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
accumulative_counts=accumulative_counts,
loss_scale='dynamic',
dtype='float16')

learning policy

More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501

param_scheduler = [
dict(
type=LinearLR,
start_factor=1e-5,
by_epoch=True,
begin=0,
end=warmup_ratio * max_epochs,
convert_to_iter_based=True),
dict(
type=CosineAnnealingLR,
eta_min=0.0,
by_epoch=True,
begin=warmup_ratio * max_epochs,
end=max_epochs,
convert_to_iter_based=True)
]

train, val, test setting

train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)

#######################################################################

PART 5 Runtime

#######################################################################

Log the dialogue periodically during the training process, optional

custom_hooks = [
dict(type=DatasetInfoHook, tokenizer=tokenizer),
dict(
type=EvaluateChatHook,
tokenizer=tokenizer,
image_processor=image_processor,
every_n_iters=evaluation_freq,
evaluation_inputs=evaluation_inputs,
evaluation_images=evaluation_images,
system=SYSTEM,
prompt_template=prompt_template)
]

configure default hooks

default_hooks = dict(
# record the time of every iteration.
timer=dict(type=IterTimerHook),
# print log every 10 iterations.
logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
# enable the parameter scheduler.
param_scheduler=dict(type=ParamSchedulerHook),
# save checkpoint per save_steps.
checkpoint=dict(
type=CheckpointHook,
by_epoch=False,
interval=save_steps,
max_keep_ckpts=save_total_limit),
# set sampler seed in distributed evrionment.
sampler_seed=dict(type=DistSamplerSeedHook),
)

configure environment

env_cfg = dict(
# whether to enable cudnn benchmark
cudnn_benchmark=False,
# set multi process parameters
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
# set distributed parameters
dist_cfg=dict(backend='nccl'),
)

set visualizer

visualizer = None

set log level

log_level = 'INFO'

load from which checkpoint

load_from = None

whether to resume training from the loaded checkpoint

resume = False

Defaults to use random seed and disable deterministic

randomness = dict(seed=None, deterministic=False)

set log processor

log_processor = dict(by_epoch=False)`

but I get the error

do you know how to solve it? thank for your help