From 601be78a3fc7813990655290016bf0343d6677e7 Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Thu, 12 Oct 2023 16:47:56 +0800
Subject: [PATCH] kcpp does sampling ourselves, we can do whatever we want

---
 common/common.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/common/common.h b/common/common.h
index fa115536b..f6a79c5d2 100644
--- a/common/common.h
+++ b/common/common.h
@@ -55,6 +55,19 @@ struct gpt_params {
     float   rope_freq_base                  = 0.0f; // RoPE base frequency
     float   rope_freq_scale                 = 0.0f; // RoPE frequency scaling factor
 
+    // sampling parameters
+    int32_t top_k             = 40;    // <= 0 to use vocab size
+    float   top_p             = 0.95f; // 1.0 = disabled
+    float   tfs_z             = 1.00f; // 1.0 = disabled
+    float   typical_p         = 1.00f; // 1.0 = disabled
+    float   temp              = 0.80f; // 1.0 = disabled
+    float   repeat_penalty    = 1.10f; // 1.0 = disabled
+    int32_t repeat_last_n     = 64;    // last n tokens to penalize (0 = disable penalty, -1 = context size)
+    float   frequency_penalty = 0.00f; // 0.0 = disabled
+    float   presence_penalty  = 0.00f; // 0.0 = disabled
+    int32_t mirostat          = 0;     // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
+    float   mirostat_tau      = 5.00f; // target entropy
+    float   mirostat_eta      = 0.10f; // learning rate
     // // sampling parameters
     struct llama_sampling_params sampling_params;