vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source
This commit is contained in:
Concedo 2024-07-14 22:25:38 +08:00
commit a33786926e
2 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/llama.cpp
View file

@ -11761,7 +11761,12 @@ struct llm_build_context {
ext_factor, attn_factor, beta_fast, beta_slow);
cb(Qcur, "Qcur", il);
Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd / n_head)));
// ref: https://github.com/google/gemma_pytorch/commit/03e657582d17cb5a8617ebf333c1c16f3694670e
switch (model.type) {
case e_model::MODEL_9B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd_head_k))); break;
case e_model::MODEL_27B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd / n_head))); break;
default: GGML_ASSERT(false);
};
cb(Qcur, "Qcur_scaled", il);
Kcur = ggml_rope_ext(