model : support classifier_pooling for rerankers (#29627)

* model : support classifier_pooling for ModernBERT rerankers

Assisted-by: Claude Opus 5.5

* model : read classifier pooling type in load_hparams

Write classifier.pooling_type from _try_set_pooling_type whenever the
config has classifier_pooling, and read it in
llama_model_base::load_hparams. ModernBERT falls back to mean when it
is unspecified.

Assisted-by: Claude Opus 5.5

* conversion : only accept cls and mean for classifier_pooling

Assisted-by: Claude Opus 5.5

* model : rename classifier_pooling_type to pooling_type_cls

Assisted-by: Claude Opus 5.5

src/llama-graph.cpp

@@ -3727,8 +3727,8 @@ void llm_graph_context::build_pooling(
             } break;
         case LLAMA_POOLING_TYPE_RANK:
             {
-                if (arch == LLM_ARCH_MODERN_BERT) {
-                    // modern bert gte reranker builds mean first then applies prediction head and classifier
+                if (hparams.pooling_type_cls == LLAMA_POOLING_TYPE_MEAN) {
+                    // modern bert with classifier_pooling = "mean" builds mean first then applies prediction head and classifier
                     // https://github.com/huggingface/transformers/blob/main/src/transformers/models/modernbert/modular_modernbert.py#L1404-1411
                     ggml_tensor * inp_mean = build_inp_mean();
                     cur = ggml_mul_mat(ctx0, ggml_cont(ctx0, ggml_transpose(ctx0, inp)), inp_mean);