happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

model : fix Granite Hybrid type check for 7B.A1B (#20795) 

* Check granite hybriid expert count to set type as LLM_TYPE_7B_A1B or LLM_TYPE_1B

* Use feed fwd dim instead of num of experts

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Victor Villar 2026-03-20 15:16:09 +01:00 committed by GitHub
parent fb78ad29bb
commit 58c81f7e81
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-model.cpp
View File

@ -2058,7 +2058,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
switch (hparams.n_embd) {
case 768: type = LLM_TYPE_350M; break;
case 1536: type = (hparams.n_embd == 2048 ? LLM_TYPE_7B_A1B : LLM_TYPE_1B); break;
case 1536: type = (hparams.n_ff() == 512 ? LLM_TYPE_7B_A1B : LLM_TYPE_1B); break;
case 2048: case 2560: type = LLM_TYPE_3B; break;
case 4096: type = LLM_TYPE_32B; break;
default: type = LLM_TYPE_UNKNOWN;