From 1881ffaf3e5f4c8a450107976f8094bd3690acfa Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sat, 7 Dec 2024 12:29:50 +0200 Subject: [PATCH] server : show curent seed in slot_params ggml-ci --- examples/server/server.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/server/server.cpp b/examples/server/server.cpp index a073279d8..0b84a3c1c 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -138,6 +138,7 @@ struct slot_params { return json { {"n_predict", n_predict}, // Server configured n_predict + {"seed", sampling.seed}, {"temperature", sampling.temp}, {"dynatemp_range", sampling.dynatemp_range}, {"dynatemp_exponent", sampling.dynatemp_exponent}, @@ -1381,7 +1382,6 @@ struct server_context { } default_generation_settings_for_props = slots[0].to_json(); - default_generation_settings_for_props["seed"] = -1; // the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens // note that n_batch can be > n_ctx (e.g. for non-causal attention models such as BERT where the KV cache is not used)