From aac36f92cee1d6f2360ed50053a90993f624d414 Mon Sep 17 00:00:00 2001 From: sharpHL <132747147+sharpHL@users.noreply.github.com> Date: Sat, 27 Jan 2024 19:20:28 +0800 Subject: [PATCH] Update llama.cpp Co-authored-by: Georgi Gerganov --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index e7b501f7b..09d2ea6dd 100644 --- a/llama.cpp +++ b/llama.cpp @@ -3979,7 +3979,7 @@ static bool llm_load_tensors( auto & layer = model.layers[i]; - layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); + layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}); layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd}); layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd});