From ebe41d49a69a46735d65e0e7fc8ae6e4b0a0fbda Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Sun, 3 Sep 2023 21:07:01 +0300
Subject: [PATCH] common : warm-up with 2 tokens - seems to work better

---
 common/common.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/common/common.cpp b/common/common.cpp
index 313821375..f72f1b84d 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -770,7 +770,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
     {
         LOG("warming up the model with an empty run\n");
 
-        const std::vector<llama_token> tmp = { llama_token_bos(lctx), };
+        const std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
         llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads);
         llama_reset_timings(lctx);
     }