books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make quote style consistent (#891)

Browse Source
This commit is contained in:
Sebastian Raschka
2025-10-21 19:42:33 -05:00
committed by GitHub
parent 9276edbc37
commit 7ca7c47e4a
24 changed files with 239 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ch05/08_memory_efficient_weight_loading/previous_chapters.py
View File

@@ -29,7 +29,7 @@ class MultiHeadAttention(nn.Module):
self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
self.out_proj = nn.Linear(d_out, d_out) # Linear layer to combine head outputs
self.dropout = nn.Dropout(dropout)
self.register_buffer('mask', torch.triu(torch.ones(context_length, context_length), diagonal=1))
self.register_buffer("mask", torch.triu(torch.ones(context_length, context_length), diagonal=1))
def forward(self, x):
b, num_tokens, d_in = x.shape