From adcb12a9bad87bc96f2f158c95892b3d04aa7ffb Mon Sep 17 00:00:00 2001
From: compilade <113953597+compilade@users.noreply.github.com>
Date: Wed, 28 Feb 2024 03:52:56 -0500
Subject: [PATCH] llama : fix non-quantization of expert gating tensors (#5754)

This reverts a single line from #5475
---
 llama.cpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/llama.cpp b/llama.cpp
index 356ca1076..893bcdbc0 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -11162,7 +11162,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
         quantize &= !params->only_copy;
 
         // do not quantize expert gating tensors
-        quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_FFN_GATE_INP, "weight");
+        // NOTE: can't use LLM_TN here because the layer number is not known
+        quantize &= name.find("ffn_gate_inp.weight") == std::string::npos;
 
         // do not quantize positional embeddings and token types (BERT)
         quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_POS_EMBD,    "weight");