From 5918c9855e52c5c64b63b8dfe9308084683b6cc5 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sun, 28 Jan 2024 09:58:56 +0200 Subject: [PATCH] Update llama.cpp --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index f1d88ecbc..2c03985b4 100644 --- a/llama.cpp +++ b/llama.cpp @@ -3970,7 +3970,7 @@ static bool llm_load_tensors( model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); { model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}); - model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); + model.output_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "bias"), {n_embd}); model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); } for (int i = 0; i < n_layer; ++i) {