mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-09 04:30:33 +00:00
hparams : refactor hparams.n_layer (#24060)
* hparams : refactor hparams.n_layer * cont : remove `n_layer_kv()`, use n_layer_all instead * cont : type consistency * pi : update SYSTEM.md * models : fix Step3.5 MTP * cont : remove duplicate switch cases * cont : explicitly set `false` to extra layers for `is_swa` and `is_recr` * cont : fix nextn layer count handling Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
+7
-3
@@ -5,10 +5,13 @@
|
||||
void llama_model_lfm2::load_arch_hparams(llama_model_loader & ml) {
|
||||
ml.get_key(LLM_KV_SHORTCONV_L_CACHE, hparams.n_shortconv_l_cache);
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
for (uint32_t il = 0; il < hparams.n_layer; ++il) {
|
||||
|
||||
for (uint32_t il = 0; il < hparams.n_layer(); ++il) {
|
||||
hparams.is_recr_impl[il] = hparams.n_head_kv(il) == 0;
|
||||
}
|
||||
hparams.n_layer_dense_lead = hparams.n_layer;
|
||||
|
||||
hparams.n_layer_dense_lead = hparams.n_layer();
|
||||
|
||||
switch (hparams.n_ff()) {
|
||||
case 4608: type = LLM_TYPE_350M; break;
|
||||
case 6912: type = LLM_TYPE_700M; break;
|
||||
@@ -16,9 +19,10 @@ void llama_model_lfm2::load_arch_hparams(llama_model_loader & ml) {
|
||||
case 10752: type = LLM_TYPE_2_6B; break;
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
|
||||
if (const auto is_swa = ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false); is_swa && hparams.n_swa > 0) {
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
|
||||
for (uint32_t il = 0; il < hparams.n_layer; ++il) {
|
||||
for (uint32_t il = 0; il < hparams.n_layer(); ++il) {
|
||||
hparams.is_swa_impl[il] = !hparams.is_recr_impl[il];
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user