model: fix all granite family parameter counts (#28643)
* model: fix all granite family parameter counts Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * model: fix additional include, add missing `A` prefix for active experts Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * model: fix code alignment, rm unused 40 block case Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> --------- Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
1 parent
434ddbbc0e
commit
d7e86430a7
5 files changed
+16
-4
No files matched your search
@@ -9,8 +9,7 @@ void llama_model_granite_moe::load_arch_hparams(llama_model_loader & ml) {
|
||||
|
||||
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;
|
||||
case 32: type = LLM_TYPE_3B_A800M; break;
|
||||
// Add additional layer/vocab/etc checks here for other model sizes
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user