From 21fe0ce4eba4e8b7744848a330d388d8eb273c65 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Thu, 13 Mar 2025 17:56:38 +0200 Subject: [PATCH] hparams : add comment [no ci] --- src/llama-hparams.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama-hparams.h b/src/llama-hparams.h index c65fbfc15..e3091c812 100644 --- a/src/llama-hparams.h +++ b/src/llama-hparams.h @@ -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;