model : add gpt-oss type strings (#15424)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 0c149cd478e9c8086967f84a8315f05a46575759..431102edea18e8529b44806d53a4fb71a6fe73eb 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -86,6 +86,7 @@ const char * llm_type_name(llm_type type) {
         case LLM_TYPE_40B:           return "40B";
         case LLM_TYPE_65B:           return "65B";
         case LLM_TYPE_70B:           return "70B";
+        case LLM_TYPE_120B:          return "120B";
         case LLM_TYPE_142B:          return "142B";
         case LLM_TYPE_236B:          return "236B";
         case LLM_TYPE_290B:          return "290B";
@@ -1834,7 +1835,11 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
                 hparams.set_swa_pattern(2);
 
-                // TODO: switch (hparams.n_layer)
+                switch (hparams.n_layer) {
+                    case 24: type = LLM_TYPE_20B; break;
+                    case 36: type = LLM_TYPE_120B; break;
+                    default: type = LLM_TYPE_UNKNOWN;
+                }
             } break;
         case LLM_ARCH_LFM2:
             {

diff --git a/src/llama-model.h b/src/llama-model.h
index 46f7d0480fabe580df5e9bc3df569942b48c4109..f639fa139811a36d4b1162b75746a4a6ec783956 100644 (file)
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -79,6 +79,7 @@ enum llm_type {
     LLM_TYPE_40B,
     LLM_TYPE_65B,
     LLM_TYPE_70B,
+    LLM_TYPE_120B,
     LLM_TYPE_142B,
     LLM_TYPE_236B,
     LLM_TYPE_290B,