replica
/
llama.cpp
mirror of https://github.com/ggml-org/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

model : make rope_yarn_log_mul optional for deepseek2 (#14896) 

* make rope_yarn_log_mul optional for deepseek2

* default rope_yarn_log_mul = 0.0f
This commit is contained in:
Gabriel Larson 2025-07-27 03:18:37 -05:00 committed by GitHub
parent 1dc9614e06
commit 4762ad7316
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-hparams.h
View File

@ -98,7 +98,7 @@ struct llama_hparams {
float rope_freq_scale_train;
float rope_freq_scale_train_swa;
uint32_t n_ctx_orig_yarn;
float rope_yarn_log_mul;
float rope_yarn_log_mul = 0.0f;
std::array<int, 4> rope_sections;

2
src/llama-model.cpp
View File

@ -1369,7 +1369,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
// that have no expert_gating_func model parameter set
hparams.expert_gating_func = LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX;
}
ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul);
ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, false);
switch (hparams.n_layer) {
case 27: type = LLM_TYPE_16B; break;