quantize : use `map` to assign quantization type from `string` (#1191)

instead of `int` (while `int` option still being supported)

This allows the following usage:

`./quantize ggml-model-f16.bin ggml-model-q4_0.bin q4_0`

instead of:

`./quantize ggml-model-f16.bin ggml-model-q4_0.bin 2`

diff --git a/.devops/tools.sh b/.devops/tools.sh
index b0196b60d5b531f655aae85f24c55216523b88a2..ece9e4efa6a09fbef977e4cbf6f151171db57e5b 100755 (executable)
--- a/.devops/tools.sh
+++ b/.devops/tools.sh
@@ -23,7 +23,7 @@ elif [[ $arg1 == '--all-in-one' || $arg1 == '-a' ]]; then
             echo "Skip model quantization, it already exists: ${i/f16/q4_0}"
         else
             echo "Converting PTH to GGML: $i into ${i/f16/q4_0}..."
-            ./quantize "$i" "${i/f16/q4_0}" 2
+            ./quantize "$i" "${i/f16/q4_0}" q4_0
         fi
     done
 else

diff --git a/README.md b/README.md
index 44cf72124635a28a707be90520713af97aef600a..509df61a172a37a51c48cf42e9fb3ae5d4940c67 100644 (file)
--- a/README.md
+++ b/README.md
@@ -203,8 +203,8 @@ python3 -m pip install -r requirements.txt
 # convert the 7B model to ggml FP16 format
 python3 convert.py models/7B/
 
-# quantize the model to 4-bits (using method 2 = q4_0)
-./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin 2
+# quantize the model to 4-bits (using q4_0 method)
+./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin q4_0
 
 # run the inference
 ./main -m ./models/7B/ggml-model-q4_0.bin -n 128

diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
index ad39a805d88e96dda7b106a35e1f88b0f0545f02..ec7f91aae6bf029187aab53160f3cd35aef34542 100644 (file)
--- a/examples/quantize/quantize.cpp
+++ b/examples/quantize/quantize.cpp
@@ -2,8 +2,17 @@
 #include "llama.h"
 
 #include <cstdio>
+#include <map>
 #include <string>
 
+static const std::map<std::string, enum llama_ftype> LLAMA_FTYPE_MAP = {
+  {"q4_0", LLAMA_FTYPE_MOSTLY_Q4_0},
+  {"q4_1", LLAMA_FTYPE_MOSTLY_Q4_1},
+  {"q4_2", LLAMA_FTYPE_MOSTLY_Q4_2},
+  {"q4_3", LLAMA_FTYPE_MOSTLY_Q4_3},
+  {"q8_0", LLAMA_FTYPE_MOSTLY_Q8_0},
+};
+
 // usage:
 //  ./quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
 //
@@ -12,11 +21,9 @@ int main(int argc, char ** argv) {
 
     if (argc < 4) {
         fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type [nthread]\n", argv[0]);
-        fprintf(stderr, "  type = %d - q4_0\n", LLAMA_FTYPE_MOSTLY_Q4_0);
-        fprintf(stderr, "  type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1);
-        fprintf(stderr, "  type = %d - q4_2\n", LLAMA_FTYPE_MOSTLY_Q4_2);
-        fprintf(stderr, "  type = %d - q4_3\n", LLAMA_FTYPE_MOSTLY_Q4_3);
-        fprintf(stderr, "  type = %d - q8_0\n", LLAMA_FTYPE_MOSTLY_Q8_0);
+        for (auto it = LLAMA_FTYPE_MAP.begin(); it != LLAMA_FTYPE_MAP.end(); it++) {
+            fprintf(stderr, "  type = \"%s\" or %d\n", it->first.c_str(), it->second);
+        }
         return 1;
     }
 
@@ -30,7 +37,18 @@ int main(int argc, char ** argv) {
     const std::string fname_inp = argv[1];
     const std::string fname_out = argv[2];
 
-    const enum llama_ftype ftype = (enum llama_ftype)atoi(argv[3]);
+    enum llama_ftype ftype;
+    if (argv[3][0] == 'q') {
+        auto it = LLAMA_FTYPE_MAP.find(argv[3]);
+        if (it == LLAMA_FTYPE_MAP.end()) {
+            fprintf(stderr, "%s: unknown ftype '%s'\n", __func__, argv[3]);
+            return 1;
+        }
+        ftype = it->second;
+    } else {
+        ftype = (enum llama_ftype)atoi(argv[3]);
+    }
+
     int nthread = argc > 4 ? atoi(argv[4]) : 0;
 
     const int64_t t_main_start_us = ggml_time_us();