配置文件位置在本地但是还是提示OSError: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.

[Asmallsoldier]

trafficstars

本地配置了本地的模型地址，还是提示无法连接远程下载 配置的文件如下 model: arch: video_llama model_type: pretrain_vicuna freeze_vit: True freeze_qformer: True max_txt_len: 512 end_sym: "###" low_resource: False

frozen_llama_proj: False

If you want use LLaMA-2-chat,

some ckpts could be download from our provided huggingface repo

i.e. https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Finetuned

llama_model: "ckpt/vicuna-13b/" or "ckpt/vicuna-7b/" or "ckpt/llama-2-7b-chat-hf" or "ckpt/llama-2-13b-chat-hf"

imagebind_ckpt_path: "ckpt/imagebind_path/"

ckpt: 'path/pretrained_visual_branch_ckpt' # you can use our pretrained ckpt from https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained/

ckpt_2: 'path/pretrained_audio_branch_ckpt'

llama_model: "/home/mao/Video-LLaMA-main/eval_configs/ckpt/Video-LLaMA-2-7B-Finetuned/llama-2-7b-chat-hf/" # or "ckpt/vicuna-7b/" or "ckpt/llama-2-7b-chat-hf" or "ckpt/llama-2-13b-chat-hf" imagebind_ckpt_path: "/home/mao/Video-LLaMA-main/eval_configs/ckpt/Video-LLaMA-2-7B-Finetuned/imagebind_huge.pth" ckpt: '/home/mao/Video-LLaMA-main/eval_configs/ckpt/Video-LLaMA-2-7B-Finetuned/VL_LLaMA_2_7B_Finetuned.pth' # you can use our pretrained ckpt from https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained/ ckpt_2: '/home/mao/Video-LLaMA-main/eval_configs/ckpt/Video-LLaMA-2-7B-Finetuned/AL_LLaMA_2_7B_Finetuned.pth' equip_audio_branch: False # whether equips the audio branch fusion_head_layers: 2 max_frame_pos: 32 fusion_header_type: "seqTransf"

datasets: webvid: vis_processor: train: name: "alpro_video_eval" n_frms: 8 image_size: 224 text_processor: train: name: "blip_caption"

run: task: video_text_pretrain 文件目录结构也都没问题都有规定的文件谁知道问题出在哪里了吗？无法运行本地的模型 下面是报错详情： /home/mao/yes/envs/videollama1/lib/python3.9/site-packages/torchvision/transforms/_functional_video.py:6: UserWarning: The 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in 0.14. Please use the 'torchvision.transforms.functional' module instead. warnings.warn( /home/mao/yes/envs/videollama1/lib/python3.9/site-packages/torchvision/transforms/_transforms_video.py:25: UserWarning: The 'torchvision.transforms._transforms_video' module is deprecated since 0.12 and will be removed in 0.14. Please use the 'torchvision.transforms' module instead. warnings.warn( Initializing Chat /home/mao/yes/envs/videollama1/lib/python3.9/site-packages/huggingface_hub/file_download.py:1150: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True. warnings.warn( Traceback (most recent call last): File "/home/mao/Video-LLaMA-main/demo_video.py", line 67, in model = model_cls.from_config(model_config).to('cuda:{}'.format(args.gpu_id)) File "/home/mao/Video-LLaMA-main/video_llama/models/video_llama.py", line 574, in from_config model = cls( File "/home/mao/Video-LLaMA-main/video_llama/models/video_llama.py", line 81, in init self.tokenizer = self.init_tokenizer() File "/home/mao/Video-LLaMA-main/video_llama/models/blip2.py", line 32, in init_tokenizer tokenizer = BertTokenizer.from_pretrained("bert-base-uncased") File "/home/mao/yes/envs/videollama1/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 1795, in from_pretrained raise EnvironmentError( OSError: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.

[pxfdjim]

请问解决这个问题了吗

[Asmallsoldier]

解决了好像

2024-12-11 10:54:28 "pxfdjim" @.***> 写道：

请问解决这个问题了吗

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>