search

360CVGroup / 360VL

Apache License 2.0
22 stars 2 forks source link

demo load ck error #2

Open changquanyou opened 2 months ago

changquanyou commented 2 months ago

from transformers import AutoModelForCausalLM, AutoTokenizer import torch from PIL import Image checkpoint = "qihoo360/360VL-8B" model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype=torch.float16, device_map='cuda', trust_remote_code=True).eval() /home/users/xiongxinlei/.conda/envs/qwen/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory warn(f"Failed to load image Python extension: {e}") Traceback (most recent call last): File "", line 1, in File "/home/users/xiongxinlei/.conda/envs/qwen/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 556, in from_pretrained return model_class.from_pretrained( File "/home/users/xiongxinlei/.conda/envs/qwen/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3375, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 631, in init self.model = QH360_VL_LlamaModel(config) File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 622, in init super(QH360_VL_LlamaModel, self).init(config) File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 448, in init self.mm_projector_ctt = build_vision_projector(config) File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 422, in build_vision_projector abstractor = build_honeybee_projector(honeybee_config,projector_type,num_tokens,lm_hidden_size) File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 399, in build_honeybee_projector abstractor = { File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 284, in init self.build_net() File "/home/users/xiongxinlei/.cache/huggingface/modules/transformers_modules/360VL-8B/modeling_360vl.py", line 334, in build_net depth = self.config.depth File "/home/users/xiongxinlei/.conda/envs/qwen/lib/python3.10/site-packages/transformers/configuration_utils.py", line 265, in getattribute return super().getattribute(key) AttributeError: 'HoneybeeVisualProjectorConfig' object has no attribute 'depth'

changquanyou commented 2 months ago
  1. 新增配置文件：visual_projector_config.json(config.json中的visual_projector_config内容)
  2. config.json 中更改配置： "mm_projector_config": "qihoo360/360VL-8B/visual_projector_config.json"