Skip to content

Support Cosyvoice2-0.5B By allowing Qwen2 architecture to have a optional bias tensor #14711

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
Jul 16, 2025
Merged

Support Cosyvoice2-0.5B By allowing Qwen2 architecture to have a optional bias tensor #14711

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
54dd8e2
support cosyvoice2 over qwen2
qwaqrm Jul 16, 2025
1095d56
Merge branch 'master' of https://github.com/tempstudio/llama.cpp
qwaqrm Jul 16, 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
5 changes: 5 additions & 0 deletions src/llama-model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2676,6 +2676,7 @@ 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}, TENSOR_NOT_REQUIRED);
output_b = create_tensor(tn(LLM_TENSOR_OUTPUT, "bias"), {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);
Expand Down Expand Up @@ -7749,6 +7750,10 @@ struct llm_build_qwen2 : public llm_graph_context {
// lm_head
cur = build_lora_mm(model.output, cur);

if (model.output_b != nullptr) {
cur = ggml_add(ctx0, cur, model.output_b);
}

cb(cur, "result_output", -1);
res->t_logits = cur;

Expand Down
Loading