Skip to content

share embeddding and output #6800

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
cccclai wants to merge 1 commit into
base: main
Choose a base branch
from
Open

share embeddding and output #6800

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 1 addition & 2 deletions examples/models/llama/llama_transformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -459,7 +459,6 @@ def __init__(self, params: ModelArgs):
for layer_id in range(params.n_layers):
self.layers.append(TransformerBlock(layer_id, params))
self.norm = RMSNorm(params.dim, eps=params.norm_eps)
self.output = nn.Linear(params.dim, params.vocab_size, bias=False)
self.use_kv_cache = params.use_kv_cache
self.generate_full_logits = params.generate_full_logits
self.max_seq_len = params.max_seq_len
Expand Down Expand Up @@ -540,7 +539,7 @@ def forward(

h = self.norm(h)

logits = self.output(h)
logits = torch.nn.functional.linear(h, self.tok_embeddings.weight)

if self.output_prune_map is not None:
# expand to original size so that downstream applications can use the logits as-is.
Expand Down
Loading