From a316a425d04027453dc0fd45f003b647c12f66f9 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Sat, 25 Mar 2023 20:26:40 +0200
Subject: Overhaul the examples structure

- main -> examples
- utils -> examples (renamed to "common")
- quantize -> examples
- separate tools for "perplexity" and "embedding"

Hope I didn't break something !
---
 quantize.cpp | 60 ------------------------------------------------------------
 1 file changed, 60 deletions(-)
 delete mode 100644 quantize.cpp

(limited to 'quantize.cpp')

diff --git a/quantize.cpp b/quantize.cpp
deleted file mode 100644
index f0230f5..0000000
--- a/quantize.cpp
+++ /dev/null
@@ -1,60 +0,0 @@
-#include "ggml.h"
-#include "llama.h"
-
-#include <cstdio>
-#include <string>
-
-const int QK = 32;
-
-// usage:
-//  ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
-//
-int main(int argc, char ** argv) {
-    ggml_time_init();
-
-    if (argc != 4) {
-        fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
-        fprintf(stderr, "  type = 2 - q4_0\n");
-        fprintf(stderr, "  type = 3 - q4_1\n");
-        return 1;
-    }
-
-    // needed to initialize f16 tables
-    {
-        struct ggml_init_params params = { 0, NULL };
-        struct ggml_context * ctx = ggml_init(params);
-        ggml_free(ctx);
-    }
-
-    const std::string fname_inp = argv[1];
-    const std::string fname_out = argv[2];
-
-    const int itype = atoi(argv[3]);
-
-    const int64_t t_main_start_us = ggml_time_us();
-
-    int64_t t_quantize_us = 0;
-
-    // load the model
-    {
-        const int64_t t_start_us = ggml_time_us();
-
-        if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), itype, QK)) {
-            fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());
-            return 1;
-        }
-
-        t_quantize_us = ggml_time_us() - t_start_us;
-    }
-
-    // report timing
-    {
-        const int64_t t_main_end_us = ggml_time_us();
-
-        printf("\n");
-        printf("%s: quantize time = %8.2f ms\n", __func__, t_quantize_us/1000.0f);
-        printf("%s:    total time = %8.2f ms\n", __func__, (t_main_end_us - t_main_start_us)/1000.0f);
-    }
-
-    return 0;
-}
-- 
cgit v1.2.3