From 19dafafd5fc7e9a01f5282566369738c241f87bd Mon Sep 17 00:00:00 2001 From: slaren Date: Wed, 3 Apr 2024 02:10:43 +0200 Subject: [PATCH] add review note --- llama.cpp | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index ab1d647d9..283ed51c0 100644 --- a/llama.cpp +++ b/llama.cpp @@ -13575,7 +13575,11 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s imatrix = it->second.data(); } else { LLAMA_LOG_INFO("\n====== %s: imatrix size %d is different from tensor size %d for %s\n", __func__, - int(it->second.size()), int(tensor->ne[0]), tensor->name); + int(it->second.size()), int(tensor->ne[0]*tensor->ne[2]), tensor->name); + // REVIEW: this can happen when quantizing an old mixtral model with split tensors with a new incompatible imatrix + // this is a significant error and it may be good idea to abort the process if this happens, + // since many people will miss the error and not realize that most of the model is being quantized without an imatrix + // tok_embd should be ignored in this case, since it always causes this warning } } }