CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Auto-fill hparams.recurrent_layer_arr based on whether the model is recurrent

Browse Source 
Branch: GraniteFour

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart
2025-05-09 15:22:18 -06:00
parent 05f1958080
commit fc9e0b576e
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-model.cpp
View File

@@ -470,6 +470,10 @@ void llama_model::load_hparams(llama_model_loader & ml) {
std::fill(hparams.n_head_arr.begin(), hparams.n_head_arr.end(), 0);
std::fill(hparams.n_head_kv_arr.begin(), hparams.n_head_kv_arr.end(), 0);
std::fill(hparams.n_ff_arr.begin(), hparams.n_ff_arr.end(), 0);
std::fill(
hparams.recurrent_layer_arr.begin(),
hparams.recurrent_layer_arr.end(),
llm_arch_is_recurrent(ml.get_arch()));
std::fill(hparams.rope_sections.begin(), hparams.rope_sections.end(), 0);