From a0dee649b8eece683f6459d77a1bb3f7228a0e92 Mon Sep 17 00:00:00 2001 From: John <78893154+cmp-nct@users.noreply.github.com> Date: Wed, 17 Jan 2024 14:38:54 +0100 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 05726c8c1..b6a2b688b 100644 --- a/llama.cpp +++ b/llama.cpp @@ -3436,7 +3436,7 @@ static bool llm_load_tensors( 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}); if (gguf_find_tensor(ml.ctx_gguf, tn(LLM_TENSOR_OUTPUT, "weight").c_str()) >= 0) { - model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); + model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}); } else { model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU ml.n_tensors++; // artificial tensor