model : full modern bert support (#18330)

* full modern bert support

* added gelu op in rank pooling for modern bert

* still working on stuff, added mean calculation before classifier head

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* first layer is dense, as per modern bert research paper

* Update src/llama-graph.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fixed set input for mean pooling to check if pooling type is ranking since modern bert does mean & rank

* Update src/llama-graph.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

src/llama-model-saver.cpp

@@ -271,6 +271,7 @@ void llama_model_saver::add_tensors_from_model() {
     add_tensor(model.cls_b);
     add_tensor(model.cls_out);
     add_tensor(model.cls_out_b);
+    add_tensor(model.cls_norm);
 
     for (const struct llama_layer & layer : model.layers) {
         for (size_t i = 0; i < sizeof(layer)/sizeof(struct ggml_tensor *); ++i) {