feat: Auto-fill hparams.recurrent_layer_arr based on whether the model is recurrent

Branch: GraniteFour

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

Author: gabe-l-hart

src/llama-model.cpp

@@ -470,6 +470,10 @@ void llama_model::load_hparams(llama_model_loader & ml) {
     std::fill(hparams.n_head_arr.begin(),    hparams.n_head_arr.end(),    0);
     std::fill(hparams.n_head_kv_arr.begin(), hparams.n_head_kv_arr.end(), 0);
     std::fill(hparams.n_ff_arr.begin(),      hparams.n_ff_arr.end(),      0);
+    std::fill(
+        hparams.recurrent_layer_arr.begin(),
+        hparams.recurrent_layer_arr.end(),
+        llm_arch_is_recurrent(ml.get_arch()));
 
     std::fill(hparams.rope_sections.begin(), hparams.rope_sections.end(), 0);