THE META KEY

元键的历史与作用
THE META KEY
If you venture into the Readline documentation, which can be found in the“READLINE” section of the bash man page, you will encounter the term metakey. On modern keyboards this maps to the ALT key, but it wasn’t always so.
Back in the dim times (before PCs but after Unix) not everybody had theirown computer. What they might have had was a device called a terminal. A terminal was a communication device that featured a text-display screen and akeyboard and had just enough electronics inside to display text characters andmove the cursor around. It was attached (usually by serial cable) to a larger computer or the communication network of a larger computer. There weremany different brands of terminals, and they all had different keyboards anddisplay feature sets. Since they all tended to at least understand ASCII, softwaredevelopers wanting portable applications wrote to the lowest common denominator. Unix systems have a very elaborate way of dealing with terminals andtheir different display features. Since the developers of Readline could not besure of the presence of a dedicated extra control key, they invented one andcalled it meta. While the ALT key serves as the meta key on modern keyboards,you can also press and release the ESC key to get the same effect as holdingdown the ALT key if you’re still using a terminal (which you can still do inLinux!).
warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.self_attn.out_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.self_attn.out_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.layer_norm1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.layer_norm1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.layer_norm2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.19.layer_norm2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.out_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.self_attn.out_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.layer_norm1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.layer_norm1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.layer_norm2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.20.layer_norm2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.out_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.self_attn.out_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.layer_norm1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.layer_norm1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.layer_norm2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.21.layer_norm2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.out_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.self_attn.out_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.layer_norm1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.layer_norm1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.layer_norm2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.22.layer_norm2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.k_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.k_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.v_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.v_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.q_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.q_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.out_proj.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.self_attn.out_proj.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.layer_norm1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.layer_norm1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.layer_norm2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.encoder.layers.23.layer_norm2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.post_layernorm.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2441: UserWarning: for vision_model.post_layernorm.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn( Traceback (most recent call last): File "C:\Users\25461\Desktop\多模态\1\GeoChat-main\geochat_demo.py", line 53, in <module> tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, args.load_8bit, args.load_4bit, device=args.device,) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\25461\Desktop\多模态\1\GeoChat-main\geochat\model\builder.py", line 125, in load_pretrained_model model = AutoModelForCausalLM.from_pretrained(model_path, low_cpu_mem_usage=True, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\transformers\models\auto\auto_factory.py", line 493, in from_pretrained return model_class.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\transformers\modeling_utils.py", line 2903, in from_pretrained ) = cls._load_pretrained_model( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\25461\AppData\Roaming\Python\Python311\site-packages\transformers\modeling_utils.py", line 3002, in _load_pretrained_model raise ValueError( ValueError: The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder` for them. Alternatively, make sure you have `safetensors` installed if the model you are using offers the weights in this format.
09-13
/home/lxng/anaconda3/envs/openfly/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for attn_pool.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta ' /home/lxng/anaconda3/envs/openfly/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for attn_pool.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta ' /home/lxng/anaconda3/envs/openfly/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for attn_pool.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta ' /home/lxng/anaconda3/envs/openfly/lib/python3.10/site-packages/torch/nn/modules/module.py:2025: UserWarning: for attn_pool.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta ' Loading checkpoint shards: 100%|███████████████████| 3/3 [00:00<00:00, 8.84it/s] [0.99803922 0.00980392 0.02941176 0.02941176 1. 0. 0. 0. ]
10-14
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值