Baike.dev
Log in
Back to tool/Back to issues
#129·llama3

Trying to set a tensor of shape torch.Size([1024, 4096]) in "weight" (which has shape torch.Size([4096, 4096])), this look incorrect.

Author: jidandan666Created Apr 23, 2024Updated Aug 6, 2025

—

Source: meta-llama/llama3

View original on GitHubView discussion on GitHub