From ed510c25d0f7b733c4a1c058a33cec084afded15 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= Date: Thu, 19 Mar 2026 15:12:19 +0100 Subject: [PATCH] llama-fit-params: fix patterns for gate_up tensors --- src/llama.cpp | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/llama.cpp b/src/llama.cpp index 872e659edc..a7cb09e3a1 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -365,14 +365,14 @@ static void llama_params_fit_impl( case LAYER_FRACTION_ATTN: { static std::array patterns; if (patterns[il].empty()) { - patterns[il] = "blk\\." + std::to_string(il) + "\\.ffn_(up|gate|down).*"; + patterns[il] = "blk\\." + std::to_string(il) + "\\.ffn_(gate|up|gate_up|down).*"; } return patterns[il].c_str(); } case LAYER_FRACTION_UP: { static std::array patterns; if (patterns[il].empty()) { - patterns[il] = "blk\\." + std::to_string(il) + "\\.ffn_(gate|down).*"; + patterns[il] = "blk\\." + std::to_string(il) + "\\.ffn_(gate|gate_up|down).*"; } return patterns[il].c_str(); } @@ -386,7 +386,7 @@ static void llama_params_fit_impl( case LAYER_FRACTION_MOE: { static std::array patterns; if (patterns[il].empty()) { - patterns[il] = "blk\\." + std::to_string(il) + "\\.ffn_(up|down|gate)_(ch|)exps"; + patterns[il] = "blk\\." + std::to_string(il) + "\\.ffn_(gate|up|gate_up|down)_(ch|)exps"; } return patterns[il].c_str(); }