From 1b8f8ad0bae57709518ec3f2ccc71320494f1367 Mon Sep 17 00:00:00 2001 From: Jean-Christophe Hoelt Date: Sun, 19 Mar 2023 18:27:54 +0200 Subject: [PATCH] Include n_predict to 2048 in examples/chatLLaMa --- examples/chatLLaMa | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/examples/chatLLaMa b/examples/chatLLaMa index 86d349e42..97c48ac87 100755 --- a/examples/chatLLaMa +++ b/examples/chatLLaMa @@ -2,17 +2,17 @@ cd "$(dirname "$0")/.." || exit -MODEL="./models/13B/ggml-model-q4_0.bin" +MODEL="${MODEL:-./models/13B/ggml-model-q4_0.bin}" USER_NAME="${USER_NAME:-User}" AI_NAME="${AI_NAME:-ChatLLaMa}" # Adjust to the number of CPU cores you want to use. N_THREAD="${N_THREAD:-8}" # Number of tokens to predict (made it larger than default because we want a long interaction) -N_PREDICTS="${N_PREDICTS:-1024}" +N_PREDICTS="${N_PREDICTS:-2048}" # Note: you can also override the generation options by specifying them on the command line: -# For example, override the context size by doing: ./chatLLaMa --ctx_size 2048 +# For example, override the context size by doing: ./chatLLaMa --ctx_size 1024 GEN_OPTIONS="${GEN_OPTIONS:---ctx_size 2048 --temp 0.7 --top_k 40 --top_p 0.5 --repeat_last_n 256 --repeat_penalty 1.17647}" # shellcheck disable=SC2086 # Intended splitting of GEN_OPTIONS