diff --git a/src/llama.cpp b/src/llama.cpp index bce9dfb07..7d220441b 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -6879,8 +6879,9 @@ static bool llm_load_tensors( const int64_t n_ff = hparams.n_ff_l(i); - ggml_context* ctx_layer = ctx_for_layer(i); - ggml_context* ctx_split = ctx_for_layer_split(i); + ggml_context * ctx_layer = ctx_for_layer(i); + ggml_context * ctx_split = ctx_for_layer_split(i); + auto & layer = model.layers[i]; layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});