diff --git a/llama.cpp b/llama.cpp
index 2f61faa9b..a30443433 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -4677,7 +4677,7 @@ static bool llm_load_tensors(
                 // output
                 {
                     model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
-                    model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, false);
+                    model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
                 }
 
                 for (int i = 0; i < n_layer; ++i) {
@@ -4692,9 +4692,9 @@ static bool llm_load_tensors(
                     layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd});
 
                     layer.ffn_gate_inp  = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), {n_embd, n_expert});
-                    layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff,   n_expert});
-                    layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff,   n_embd, n_expert});
-                    layer.ffn_up_exps   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {n_embd, n_ff,   n_expert});
+                    layer.ffn_gate_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE_EXPS, i), {n_embd, n_ff,   n_expert});
+                    layer.ffn_down_exps = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN_EXPS, i), {n_ff,   n_embd, n_expert});
+                    layer.ffn_up_exps   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP_EXPS,   i), {n_embd, n_ff,   n_expert});
 
                     layer.layer_out_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_LAYER_OUT_NORM, "weight", i), {n_embd});
                 }