Change llama_tokenize return meaning

llama.cpp

@@ -1455,7 +1455,7 @@ int llama_tokenize(
 
     if (n_max_tokens < (int) res.size()) {
         fprintf(stderr, "%s: too many tokens\n", __func__);
-        return 1;
+        return -((int) res.size());
     }
 
     for (size_t i = 0; i < res.size(); i++) {

llama.h

@@ -89,7 +89,7 @@ extern "C" {
     // Convert the provided text into tokens.
     // The tokens pointer must be large enough to hold the resulting tokens.
     // Returns the number of tokens on success, no more than n_max_tokens
-    // Returns -1 on failure
+    // Returns a negative number on failure - the number of tokens that would have been returned
     // TODO: not sure if correct
     LLAMA_API int llama_tokenize(
             struct llama_context * ctx,

main.cpp

@@ -155,6 +155,7 @@ void sigint_handler(int signo) {
 #endif
 
 int main(int argc, char ** argv) {
+    // has to be called once at the start of the program to init ggml stuff
     ggml_time_init();
 
     gpt_params params;