CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

hparams : add comment [no ci]

Browse Source
This commit is contained in:
Georgi Gerganov
2025-03-13 17:56:38 +02:00
parent de9d18fa9c
commit 21fe0ce4eb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-hparams.h
View File

@@ -36,7 +36,7 @@ struct llama_hparams {
uint32_t n_layer;
uint32_t n_rot;
uint32_t n_swa = 0; // sliding window attention (SWA)
uint32_t n_swa_pattern = 1;
uint32_t n_swa_pattern = 1; // by default, all layers use non-sliding-window attention
uint32_t n_embd_head_k; // dimension of keys (d_k). d_q is assumed to be the same, but there are n_head q heads, and only n_head_kv k-v heads
uint32_t n_embd_head_v; // dimension of values (d_v) aka n_embd_head
uint32_t n_expert = 0;