Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-10 23:09:17 +02:00
Code Issues Packages Projects Releases Wiki Activity

model: fix granite3 moe unknown parameter count (#28632)

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2026-09-09 16:46:22 +08:00
committed by GitHub
parent 6de9cdb26b
commit e2d2c0d6aa
3 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+1
View File
@@ -935,6 +935,7 @@ 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_1B_A400M: return "1B.A400M";
case LLM_TYPE_7B_A1B: return "7B.A1B";
case LLM_TYPE_8B_A1B: return "8B.A1B";
case LLM_TYPE_7_9B_A1_3B: return "7.9B.A1.3B";
src/llama-model.h
+1
View File
@@ -116,6 +116,7 @@ enum llm_type {
LLM_TYPE_17B_16E, // llama4 Scout
LLM_TYPE_17B_128E, // llama4 Maverick
LLM_TYPE_A13B,
LLM_TYPE_1B_A400M, // Granite3 MoE
LLM_TYPE_7B_A1B,
LLM_TYPE_8B_A1B, // lfm2moe
LLM_TYPE_7_9B_A1_3B, // Ling-3.0-tiny
src/models/granite-moe.cpp
+1
View File
@@ -8,6 +8,7 @@ void llama_model_granite_moe::load_arch_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ATTENTION_SCALE, hparams.f_attention_scale, false);
switch (hparams.n_layer()) {
case 24: type = LLM_TYPE_1B_A400M; break;
case 32: type = LLM_TYPE_3B; break;
case 40: type = LLM_TYPE_3B; break;
// Add additional layer/vocab/etc checks here for other model sizes