llama-model: read final_logit_softcapping for Gemma 4 (#21390)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index ba935340fcf95f1df70c1cbac9d5fbe3d9d26dde..79d08ff41e3dffa1937681de1c6ddcefe8c623c6 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1279,6 +1279,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 ml.get_key(LLM_KV_EMBEDDING_LENGTH_PER_LAYER,  hparams.n_embd_per_layer);
                 ml.get_key(LLM_KV_ATTENTION_KEY_LENGTH_SWA,    hparams.n_embd_head_k_swa);
                 ml.get_key(LLM_KV_ATTENTION_VALUE_LENGTH_SWA,  hparams.n_embd_head_v_swa);
+                ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING,     hparams.f_final_logit_softcapping, false);
 
                 switch (hparams.n_layer) {
                     case 35: type = LLM_TYPE_E2B; break;