model : support granite multilingual embeddings R2 (ibm-granite/granite-embedding-{97,311}m-multilingual-r2) (#22716)

* Add support for the ibm-granite/granite-embedding-{97m,311m}-multilingual-r2 embedding models:

* Added a version of the gpt4o tokenizer that has a fixed regex (better handling of marks), and different token merging setting for the 97m model
* Reused gemma4 tokenizer for the 311m model

* granite-embedding-*-multilingual-r2 : add support SwiGLU FFN for Granite Embedding Multilingual R2

* added new GGUF key <arch>.hidden_activation (LLM_KV_HIDDEN_ACT) + writer
* added a forward declaration of llm_ffn_op_type to llama-hparams.h
* added llm_ffn_op in hparams
* added LLM_FFN_NONE = 0 sentinel to llm_ffn_op_type (value-initialization), modern-bert: explicitly assigns LLM_FFN_GEGLU before reading GGUF (unchanged).
* centralized hidden_act mapping in llama-model.cpp, added llm_ffn_op_type_from_string() helper, mirroring rope_scaling_type/llama_rope_scaling_type_from_string()
* modern-bert reads the GGUF key (when present) and uses the resulting op in its FFN graph

* Added granite-embedding-{97m,311m}-multilingual-r2 to the converter code

* Added the hashes for the granite embedding multilingual R2 models
* Set the hidden_activation in the GGUF if the field is present in config.json (such as for the granite embedding models)

src/models/modern-bert.cpp

@@ -14,6 +14,14 @@ void llama_model_modern_bert::load_arch_hparams(llama_model_loader & ml) {
 
     ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
 
+    // Some ModernBert derivatives (e.g. IBM Granite Embedding 97m R2) use
+    // SiLU/SwiGLU in the FFN instead of the default GELU/GeGLU.
+    hparams.llm_ffn_op = LLM_FFN_GEGLU;
+    std::string hidden_act;
+    if (ml.get_key(LLM_KV_HIDDEN_ACT, hidden_act, false)) {
+        hparams.llm_ffn_op = llm_ffn_op_type_from_string(hidden_act, LLM_FFN_GEGLU);
+    }
+
     switch (hparams.n_layer) {
         case 12:
             type = LLM_TYPE_47M; break; // granite-embedding-small
@@ -144,7 +152,8 @@ llama_model_modern_bert::graph::graph(const llama_model & model, const llm_graph
                 NULL,                      NULL, NULL,
                 model.layers[il].ffn_down, NULL, NULL,
                 NULL,
-                LLM_FFN_GEGLU, LLM_FFN_SEQ, il);
+                hparams.llm_ffn_op,
+                LLM_FFN_SEQ, il);
 
         // attentions bypass the intermediate layer
         cur = ggml_add(ctx0, cur, ffn_inp);