model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)

* model: EmbeddingGemma sentence-transformers dense linear projections support

* model: add support for EmbeddingGemma SentenceTransformers dense linear projections

Adding support for the Dense modules used in EmbeddingGemma models.
EmbeddingGemma is a SentenceTransformers model with additional modules beyond the base Transformer backbone.

See: https://developers.googleblog.com/en/gemma-explained-embeddinggemma-architecture-and-recipe/

* model: add support for EmbeddingGemma SentenceTransformers dense linear projections

- converting model with dense-layers is optional
- introduced dense config params

* Update convert_hf_to_gguf.py

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>

* fixed formatting issues

* Update src/llama-graph.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* - removed pooling_type_opt, always allow overriding pooling_type
- asserts checking dense features dims

* fix python lint

* fix ubuntu gcc build warning

* - fixed thread-safety test
- moved asserts to load_hparams

* - tidying up code
- simplifying graph-context expecting both dense weights

* minor : add TODO

---------

Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

src/llama-hparams.h

@@ -169,6 +169,12 @@ struct llama_hparams {
     uint32_t laurel_rank  = 64;
     uint32_t n_embd_altup = 256;
 
+    // needed for sentence-transformers dense layers
+    uint32_t dense_2_feat_in  = 0;  // in_features of the 2_Dense
+    uint32_t dense_2_feat_out = 0;  // out_features of the 2_Dense
+    uint32_t dense_3_feat_in  = 0;  // in_features of the 3_Dense
+    uint32_t dense_3_feat_out = 0;  // out_features of the 3_Dense
+
     // xIELU
     std::array<float, LLAMA_MAX_LAYERS> xielu_alpha_n;
     std::array<float, LLAMA_MAX_LAYERS> xielu_alpha_p;