From aa12d8a81f5b2cf6d9b7a037fa69bdec6ca036b1 Mon Sep 17 00:00:00 2001 From: eiery <19350831+eiery@users.noreply.github.com> Date: Sun, 23 Apr 2023 20:56:40 -0400 Subject: [PATCH] Update llama.py update n_batch default to 512 to match upstream llama.cpp --- llama_cpp/llama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama_cpp/llama.py b/llama_cpp/llama.py index ea9f0ff..a414a1c 100644 --- a/llama_cpp/llama.py +++ b/llama_cpp/llama.py @@ -37,7 +37,7 @@ class Llama: use_mlock: bool = False, embedding: bool = False, n_threads: Optional[int] = None, - n_batch: int = 8, + n_batch: int = 512, last_n_tokens_size: int = 64, lora_base: Optional[str] = None, lora_path: Optional[str] = None,