From 8f644a0a859938c787d329d27f98e03c58d7df27 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Tue, 21 Mar 2023 17:32:14 +0200
Subject: [PATCH] Change default repeat_penalty to 1.0
I feel this penalty is not really helping.
Especially for the example from the README it makes results pretty bad
---
utils.h | 31 +++++++++++++++----------------
1 file changed, 15 insertions(+), 16 deletions(-)
diff --git a/utils.h b/utils.h
index 971cc0e..4aa7c63 100644
--- a/utils.h
+++ b/utils.h
@@ -13,33 +13,32 @@
//
struct gpt_params {
- int32_t seed = -1; // RNG seed
- int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
- int32_t n_predict = 128; // new tokens to predict
+ int32_t seed = -1; // RNG seed
+ int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
+ int32_t n_predict = 128; // new tokens to predict
int32_t repeat_last_n = 64; // last n tokens to penalize
- int32_t n_ctx = 512; //context size
- bool memory_f16 = false; // use f16 instead of f32 for memory kv
+ int32_t n_ctx = 512; //context size
// sampling parameters
int32_t top_k = 40;
float top_p = 0.95f;
float temp = 0.80f;
- float repeat_penalty = 1.30f;
+ float repeat_penalty = 1.10f;
int32_t n_batch = 8; // batch size for prompt processing
- std::string model = "models/lamma-7B/ggml-model.bin"; // model path
- std::string prompt = "";
+ std::string model = "models/lamma-7B/ggml-model.bin"; // model path
+ std::string prompt = "";
- bool random_prompt = false;
-
- bool use_color = false; // use color to distinguish generations and inputs
-
- bool interactive = false; // interactive mode
- bool interactive_start = false; // reverse prompt immediately
std::vector<std::string> antiprompt; // string upon seeing which more user input is prompted
- bool instruct = false; // instruction mode (used for Alpaca models)
- bool ignore_eos = false; // do not stop generating after eos
+
+ bool memory_f16 = false; // use f16 instead of f32 for memory kv
+ bool random_prompt = false; // do not randomize prompt if none provided
+ bool use_color = false; // use color to distinguish generations and inputs
+ bool interactive = false; // interactive mode
+ bool interactive_start = false; // reverse prompt immediately
+ bool instruct = false; // instruction mode (used for Alpaca models)
+ bool ignore_eos = false; // do not stop generating after eos
};
bool gpt_params_parse(int argc, char ** argv, gpt_params & params);