From 94f330ad45d1b311b6c2b3452c15f196c1d6ef25 Mon Sep 17 00:00:00 2001
From: John <78893154+cmp-nct@users.noreply.github.com>
Date: Tue, 16 Jan 2024 15:21:13 +0100
Subject: [PATCH] falcon arch fix for tied output embeddings

---
 llama.cpp | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/llama.cpp b/llama.cpp
index 46c4d11c8..5565fd41e 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -3435,7 +3435,11 @@ 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});
-                        model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
+                        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});
+                        } else {
+                            model.output = model.tok_embd;
+                        }
                     }
 
                     for (int i = 0; i < n_layer; ++i) {