restore pertinent logs

Author: Nexesenex

llama.cpp

@@ -3214,7 +3214,6 @@ struct llama_model_loader {
 
         // determine file type based on the number of tensors for each quantization and print meta data
         // TODO: make optional
-        if(false) //disable this log for now
         {
             std::map<enum ggml_type, uint32_t> n_type;
 
@@ -4892,9 +4891,21 @@ static void llm_load_print_meta(llama_model_loader & ml, llama_model & model) {
         LLAMA_LOG_INFO("%s: model params     = %.2f K\n", __func__, ml.n_elements*1e-3);
     }
     if (ml.n_bytes < GiB) {
+        LLAMA_LOG_INFO("%s: model size       = %.2f Bytes (%.2f BPW) \n", __func__, ml.n_bytes/1.0,                    ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f KiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0,               ml.n_bytes*8.0/ml.n_elements);
         LLAMA_LOG_INFO("%s: model size       = %.2f MiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0/1024.0,        ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f GiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0/1024.0/1024.0, ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f KB (%.2f BPW) \n", __func__, ml.n_bytes/1000.0,               ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f MB (%.2f BPW) \n", __func__, ml.n_bytes/1000.0/1000.0       , ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f GB (%.2f BPW) \n", __func__, ml.n_bytes/1000.0/1000.0/1000.0, ml.n_bytes*8.0/ml.n_elements);
     } else {
+        LLAMA_LOG_INFO("%s: model size       = %.2f Bytes (%.2f BPW) \n", __func__, ml.n_bytes/1.0,                    ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f KiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0,               ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f MiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0/1024.0       , ml.n_bytes*8.0/ml.n_elements);
         LLAMA_LOG_INFO("%s: model size       = %.2f GiB (%.2f BPW) \n", __func__, ml.n_bytes/1024.0/1024.0/1024.0, ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f KB (%.2f BPW) \n", __func__, ml.n_bytes/1000.0,               ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f MB (%.2f BPW) \n", __func__, ml.n_bytes/1000.0/1000.0       , ml.n_bytes*8.0/ml.n_elements);
+        LLAMA_LOG_INFO("%s: model size       = %.2f GB (%.2f BPW) \n", __func__, ml.n_bytes/1000.0/1000.0/1000.0, ml.n_bytes*8.0/ml.n_elements);
     }
 
     // general kv