From 6c7fd67b647a76846d1691cd181011dff4549d02 Mon Sep 17 00:00:00 2001
From: piDack <104877312+piDack@users.noreply.github.com>
Date: Wed, 7 May 2025 15:23:11 +0800
Subject: [PATCH] llama : support tie embedding for chatglm models (#13328)

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

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 8d25070f4..774e343fb 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -3510,7 +3510,11 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
 
                     // output
                     output_norm   = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
-                    output        = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, 0);
+                    output        = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
+                    // if output is NULL, init from the input tok embed
+                    if (output == NULL) {
+                        output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
+                    }
 
                     for (int i = 0; i < n_layer; ++i) {
                         auto & layer = layers[i];