llama : fix MiniCPM (#5392)

* fix bug for norm_rms_eps missing

* to align with the same order as convert.py for model write

* fix: undo HF models permute tensor

* update for flake8 lint

1 files changed, 2 insertions, 0 deletions

diff --git a/llama.cpp b/llama.cpp
index f8f5796a..552e0d02 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -2947,6 +2947,8 @@ static void llm_load_hparams(
             } break;
         case LLM_ARCH_MINICPM:
             {
+                ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+
                 switch (hparams.n_layer) {
                     case 40: model.type = e_model::MODEL_2B; break;
                     default: model.type = e_model::MODEL_UNKNOWN;