You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
首先感谢你们的文章!看了很有启发性。
我有一点困惑,对于文中提到的取llama模型的语义特征,并且你们提到了下面这两行:
for layer in self.layers:
h = layer(h, start_pos, freqs_cis, mask)
我使用了你们的例子输入”a colorful animal with big eyes on a blue background,“但当我打印第40层layer的最终结果shape时,显示h的shape是【1, 12, 5120】,显然每个word都拥有一个[5120]长度的token,但你们的sur_data_small里面却是一个【5120】的token,这是怎么回事呢?我应该取LLM哪个位置的语义特征呢?
期待你们的回复
The text was updated successfully, but these errors were encountered:
首先感谢你们的文章!看了很有启发性。
我有一点困惑,对于文中提到的取llama模型的语义特征,并且你们提到了下面这两行:
for layer in self.layers:
h = layer(h, start_pos, freqs_cis, mask)
我使用了你们的例子输入”a colorful animal with big eyes on a blue background,“但当我打印第40层layer的最终结果shape时,显示h的shape是【1, 12, 5120】,显然每个word都拥有一个[5120]长度的token,但你们的sur_data_small里面却是一个【5120】的token,这是怎么回事呢?我应该取LLM哪个位置的语义特征呢?
期待你们的回复
The text was updated successfully, but these errors were encountered: