From 544fc08db237aaf3eacad27c01d641a80aa547bc Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Sun, 17 May 2026 14:24:04 +0000 Subject: [PATCH] Check for output_extra.weight when loading Gemma4 assistant models --- src/llama-load-tensors.cpp | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/src/llama-load-tensors.cpp b/src/llama-load-tensors.cpp index b284e248..bd81e060 100644 --- a/src/llama-load-tensors.cpp +++ b/src/llama-load-tensors.cpp @@ -2150,6 +2150,10 @@ bool create_tensors_helper::create_gemma4_mtp_tensors(const LLM_TN & tn) { model.tok_embd = create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); model.output_norm = create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0); model.output = create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED); + auto output_extra = create_tensor(ctx_output, "output_extra.weight", {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED); + if (output_extra) { + model.output = output_extra; + } if (model.output == NULL) { model.output = create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_DUPLICATED); }