model : add Granite Hybrid types (#16635)

add Granite 4 models mapping their embedding dimensions to the # of
parameters.

Information taken from https://huggingface.co/ibm-granite/granite-4.0-h-tiny

Signed-off-by: Giuseppe Scrivano <redacted>

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 522d1f67da3cb93c5f33cc4b01c9e5757616841c..909b49e8e645002723233a7eadb3b465ea9bd97e 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -114,6 +114,7 @@ const char * llm_type_name(llm_type type) {
         case LLM_TYPE_17B_16E:       return "17Bx16E (Scout)";
         case LLM_TYPE_17B_128E:      return "17Bx128E (Maverick)";
         case LLM_TYPE_A13B:          return "A13B";
+        case LLM_TYPE_7B_A1B:        return "7B.A1B";
         case LLM_TYPE_8B_A1B:        return "8B.A1B";
         case LLM_TYPE_21B_A3B:       return "21B.A3B";
         case LLM_TYPE_30B_A3B:       return "30B.A3B";
@@ -1843,8 +1844,10 @@ void llama_model::load_hparams(llama_model_loader & ml) {
 
                 ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
 
-                switch (hparams.n_layer) {
-                    // TODO: Add llm type label (not sure this is useful)
+                switch (hparams.n_embd) {
+                    case 1536: type = LLM_TYPE_7B_A1B; break;
+                    case 2048: case 2560: type = LLM_TYPE_3B; break;
+                    case 4096: type = LLM_TYPE_32B; break;
                     default: type = LLM_TYPE_UNKNOWN;
                 }
 

diff --git a/src/llama-model.h b/src/llama-model.h
index 7f48662f2807ac46e6b24335e850e3585b1575ed..05701e7d70c84a762057eedfdcefae512676059d 100644 (file)
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -107,6 +107,7 @@ enum llm_type {
     LLM_TYPE_17B_16E, // llama4 Scout
     LLM_TYPE_17B_128E, // llama4 Maverick
     LLM_TYPE_A13B,
+    LLM_TYPE_7B_A1B,
     LLM_TYPE_8B_A1B, // lfm2moe
     LLM_TYPE_21B_A3B, // Ernie MoE small
     LLM_TYPE_30B_A3B,