8000 Support tie embedding for chatglm models by piDack · Pull Request #13328 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Support tie embedding for chatglm models #13328

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

Merged
merged 2 commits into from
May 7, 2025
Merged

Support tie embedding for chatglm models #13328

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5ba8f23
support tie embedding for chatglm models
piDack May 6, 2025
5aaf38c
Update src/llama-model.cpp
piDack May 7, 2025
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
Next Next commit
support tie embedding for chatglm models
  • Loading branch information
@piDack
piDack committed May 6, 2025
commit 5ba8f23b67086d75ab2723e1aed91c6ff59b4636
6 changes: 5 additions & 1 deletion src/llama-model.cpp
View file 8000
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3510,7 +3510,11 @@ bool llama_model::load_tensors(llama_model_loader & ml) {

// output
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}

for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];
Expand Down
Loading
0