model : remove unnecessary prefix for tensor loading constants

Co-authored-by: Sigbjørn Skjæret <[email protected]>

Author: compilade

src/llama-model.cpp

@@ -3220,10 +3220,10 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                     {
                         output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
 
-                        output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
                         // if output is NULL, init from the input tok embed, duplicated to allow offloading
                         if (output == NULL) {
-                            output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_DUPLICATED);
+                            output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
                         }
                     }
 
@@ -3266,10 +3266,10 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
                     {
                         output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
 
-                        output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
                         // if output is NULL, init from the input tok embed, duplicated to allow offloading
                         if (output == NULL) {
-                            output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, llama_model_loader::TENSOR_DUPLICATED);
+                            output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
                         }
                     }
 
@@ -3316,7 +3316,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
 
                         layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
 
-                        layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, llama_model_loader::TENSOR_NOT_REQUIRED);
+                        layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, TENSOR_NOT_REQUIRED);
 
                         if (layer.ffn_gate_inp) {
                             // MoE