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.h

@@ -475,6 +475,7 @@ struct llama_model {
     struct ggml_tensor * cls_b     = nullptr;
     struct ggml_tensor * cls_out   = nullptr;
     struct ggml_tensor * cls_out_b = nullptr;
+    struct ggml_tensor * cls_norm  = nullptr;
 
     struct ggml_tensor * conv1d   = nullptr;
     struct ggml_tensor * conv1d_b = nullptr;