这里好像有点问题

[marcury6]

transformers下载并更新到最新版本。把huggingface上面关于模型的文件都下载了，也通过 pip install --upgrade torch命令下载最新的Pytorch库。并访问英伟达toolkit仓库下载toolkit12.4.1版本，最后终端运行了

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124

还是出现报错

报错信息

Traceback (most recent call last): File "C:\Users\Administrator\Desktop\Qwen2-Boundless-main\continuous_conversation.py", line 10, in model = AutoModelForCausalLM.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\python\Lib\site-packages\transformers\models\auto\auto_factory.py", line 564, in from_pretrained return model_class.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\python\Lib\site-packages\transformers\modeling_utils.py", line 3318, in from_pretrained raise ImportError( ImportError: Using low_cpu_mem_usage=True or a device_map requires Accelerate: pip install accelerate

[marcury6]

看漏了报错信息，终端运行 pip install accelerate 得到解决

最后运行时有两条奇怪的提醒

Assistant: The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results. E:\python\Lib\site-packages\transformers\models\qwen2\modeling_qwen2.py:580: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:555.) attn_output = torch.nn.functional.scaled_dot_product_attention(

[ystemsrx]

这两个警告没有什么大影响，一个是Attention Mask 没有设置，还有一个是没有编译 Flash Attention，可以不用处理