Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-04 02:37:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

model : load relevant arrays with n_layer_all (#28173)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2026-09-01 19:58:29 +03:00
committed by GitHub
parent c845263f8b
commit d11b3cc7ed
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+3 -3
View File
@@ -1284,8 +1284,8 @@ void llama_model_base::load_hparams(llama_model_loader & ml) {
std::fill(hparams.swiglu_clamp_exp.begin(), hparams.swiglu_clamp_exp.end(), 0.0f);
std::fill(hparams.swiglu_clamp_shexp.begin(), hparams.swiglu_clamp_shexp.end(), 0.0f);
ml.get_key_or_arr(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, hparams.n_layer(), false);
ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, hparams.n_layer(), false);
ml.get_key_or_arr(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, hparams.n_layer_all, false);
ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, hparams.n_layer_all, false);
// Populate deepstack_mapping_arr - initialized to -1 (no deepstack)
std::fill(hparams.deepstack_mapping_arr.begin(), hparams.deepstack_mapping_arr.end(), -1);
@@ -1293,7 +1293,7 @@ void llama_model_base::load_hparams(llama_model_loader & ml) {
// n_head_kv is optional, default to n_head
hparams.n_head_kv_arr = hparams.n_head_arr;
ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT_KV, hparams.n_head_kv_arr, hparams.n_layer(), false);
ml.get_key_or_arr(LLM_KV_ATTENTION_HEAD_COUNT_KV, hparams.n_head_kv_arr, hparams.n_layer_all, false);
bool rope_finetuned = false;
ml.get_key(LLM_KV_ROPE_SCALING_FINETUNED, rope_finetuned, false);