From 36e6685d932f43d65dc1bdf2a5efb3145d0bd000 Mon Sep 17 00:00:00 2001 From: pculliton Date: Wed, 31 Jul 2024 11:00:16 -0400 Subject: [PATCH] Update src/llama.cpp Co-authored-by: slaren --- src/llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama.cpp b/src/llama.cpp index fba6b1757..e6f303d31 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -11737,7 +11737,7 @@ struct llm_build_context { // ref: https://github.com/google/gemma_pytorch/commit/03e657582d17cb5a8617ebf333c1c16f3694670e switch (model.type) { - case e_model::MODEL_2B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd_head_k))); break; + case e_model::MODEL_2B: case e_model::MODEL_9B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd_head_k))); break; case e_model::MODEL_27B: Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd / n_head))); break; default: GGML_ABORT("fatal error");