I give an image and a prompt the model but I get this error: got multiple values for keyword argument 'return_dict'.
My code:

from transformers import AutoTokenizer, AutoModel, CLIPImageProcessor
from PIL import Image
import torch
import os
import math

#os.environ["CUDA_VISIBLE_DEVICES"] = "3"
def split_model(model_name):
device_map = {}
world_size = torch.cuda.device_count()
num_layers = {'InternVL-Chat-V1-2': 60, 'InternVL-Chat-V1-2-Plus': 60}[model_name]
# Since the first GPU will be used for ViT, treat it as half a GPU.
num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
num_layers_per_gpu = [num_layers_per_gpu] * world_size
num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
layer_cnt = 0
print("num_layers_per_gpu",num_layers_per_gpu)
for i, num_layer in enumerate(num_layers_per_gpu):
for j in range(num_layer):
device_map[f'language_model.model.layers.{layer_cnt}'] = i
layer_cnt += 1
device_map['vision_model'] = 3
device_map['mlp1'] = 3
device_map['language_model.model.tok_embeddings'] = 3
device_map['language_model.model.embed_tokens'] = 2
device_map['language_model.output'] = 3
device_map['language_model.model.norm'] = 3
device_map['language_model.model.rotary_emb'] = 3
device_map['language_model.lm_head'] = 3
device_map[f'language_model.model.layers.{num_layers - 1}'] = 3
print("device_map",device_map)
return device_map

path = "OpenGVLab/InternVL-Chat-V1-2"
device_map = split_model('InternVL-Chat-V1-2')
model = AutoModel.from_pretrained(
path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
use_flash_attn=True,
trust_remote_code=True,
device_map=device_map).eval()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
image_processor = CLIPImageProcessor.from_pretrained(path)
image = Image.open('......jpg').resize((448, 448))

Görsel

pixel_values = image_processor(images=image, return_tensors='pt').pixel_values.to(torch.bfloat16)
generation_config = dict(max_new_tokens=1024, do_sample=True)

Modelin chat formatına göre input oluştur

question = '\nVerilen belge içerisinden şu bilgileri çıkar .....'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'User: {question}')
print(f'Assistant: {response}')