fix trailing whitespace

Author: ymcki

src/llama.cpp

@@ -7757,9 +7757,9 @@ static bool llm_load_tensors(
                     }
                 } break;
             case LLM_ARCH_DECI:
-                {   
+                {
                     model.tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
-            
+
                     // output
                     model.output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
                     model.output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED);
@@ -11028,9 +11028,9 @@ struct llm_build_context {
     }
 
     struct ggml_cgraph * build_deci() {
-        struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, llama_model_max_nodes(model), false);      
+        struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, llama_model_max_nodes(model), false);
 
-        // mutable variable, needed during the last layer of the computation to skip unused tokens  
+        // mutable variable, needed during the last layer of the computation to skip unused tokens
         int32_t n_tokens = this->n_tokens;
 
         const int64_t n_embd_head = hparams.n_embd_head_v;
@@ -11054,9 +11054,9 @@ struct llm_build_context {
             const int64_t n_head_kv = hparams.n_head_kv(il);
             const int64_t n_head    = hparams.n_head(il);
 
-            if (n_head == 0) // attention-free layer of Llama-3_1-Nemotron-51B
+            if (n_head == 0) { // attention-free layer of Llama-3_1-Nemotron-51B
                 cur = inpL;
-            else {
+	    } else {
                 // norm
                 cur = llm_build_norm(ctx0, inpL, hparams,
                         model.layers[il].attn_norm, NULL,
@@ -11067,9 +11067,8 @@ struct llm_build_context {
             if (n_head > 0 && n_head_kv == 0) { // "linear attention" of Llama-3_1-Nemotron-51B
                 cur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wo, cur);
                 cb(cur, "wo", il);
-            } else if (n_head > 0)
+            } else if (n_head > 0) {
             // self-attention
-            {
                 // rope freq factors for llama3; may return nullptr for llama2 and other models
                 struct ggml_tensor * rope_factors = build_rope_factors(il);