mirror of
https://github.com/karpathy/minGPT
synced 2024-05-18 05:26:03 +02:00
i know it doesn't look like much, but this kwarg was not used lol :D
This commit is contained in:
parent
107b6d7e31
commit
3ed14b2cec
|
@ -58,7 +58,7 @@ class CausalSelfAttention(nn.Module):
|
|||
.view(1, 1, config.block_size, config.block_size))
|
||||
self.n_head = config.n_head
|
||||
|
||||
def forward(self, x, layer_past=None):
|
||||
def forward(self, x):
|
||||
B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
|
||||
|
||||
# calculate query, key, values for all heads in batch and move head forward to be the batch dim
|
||||
|
|
Loading…
Reference in New Issue