mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-10-17 20:03:45 +02:00
talk-llama : sync llama.cpp
This commit is contained in:
@@ -207,7 +207,7 @@ llama_model_gemma3::graph<iswa>::graph(const llama_model & model, const llm_grap
|
||||
res->t_embd = cur;
|
||||
|
||||
// lm_head
|
||||
cur = build_lora_mm(model.output, cur);
|
||||
cur = build_lora_mm(model.output, cur, model.output_s);
|
||||
|
||||
if (hparams.f_final_logit_softcapping) {
|
||||
cur = ggml_scale(ctx0, cur, 1.0f / hparams.f_final_logit_softcapping);
|
||||
|
||||
Reference in New Issue
Block a user