Skip to content

Fix: Correct spelling of 'mh_ouput' to 'mh_output' #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
junkim100 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix: Correct spelling of 'mh_ouput' to 'mh_output' #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2ac8cc3
Fix spelling error
junkim100 Oct 28, 2024
602863b
Fix spelling error
junkim100 Oct 28, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion makeMoE_Concise.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -441,7 +441,7 @@
"\n",
" \n",
" def forward(self, mh_output):\n",
" # mh_ouput is the output tensor from multihead self attention block\n",
" # mh_output is the output tensor from multihead self attention block\n",
" logits = self.topkroute_linear(mh_output)\n",
"\n",
" #Noise logits\n",
Expand Down
4 changes: 2 additions & 2 deletions makeMoE_from_Scratch.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1393,8 +1393,8 @@
" self.top_k = top_k\n",
" self.linear =nn.Linear(n_embed, num_experts)\n",
"\n",
" def forward(self, mh_ouput):\n",
" # mh_ouput is the output tensor from multihead self attention block\n",
" def forward(self, mh_output):\n",
" # mh_output is the output tensor from multihead self attention block\n",
" logits = self.linear(mh_output)\n",
" top_k_logits, indices = logits.topk(self.top_k, dim=-1)\n",
" zeros = torch.full_like(logits, float('-inf'))\n",
Expand Down