From db44ddf81970e0d800d899e361b41d1b4519f12d Mon Sep 17 00:00:00 2001 From: sharpHL <132747147+sharpHL@users.noreply.github.com> Date: Sat, 27 Jan 2024 19:20:02 +0800 Subject: [PATCH] Update llama.cpp Co-authored-by: Georgi Gerganov --- llama.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/llama.cpp b/llama.cpp index 4a5c7d09e..e7b501f7b 100644 --- a/llama.cpp +++ b/llama.cpp @@ -3987,8 +3987,8 @@ static bool llm_load_tensors( layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}); layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}); - layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); - layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); + layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}); + layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i), {n_embd}); layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}); layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd});