From 95fd0f075eaefb2f4782ad8158004848cf322492 Mon Sep 17 00:00:00 2001 From: kingbri Date: Sun, 17 Dec 2023 23:31:58 -0500 Subject: [PATCH] Model: Fix no flash attention Was being called wrong from config. Signed-off-by: kingbri --- model.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model.py b/model.py index 5f6f603..2aed565 100644 --- a/model.py +++ b/model.py @@ -94,7 +94,7 @@ class ModelContainer: ) # Turn off flash attention? - self.config.no_flash_attn = unwrap(kwargs.get("no_flash_attn"), False) + self.config.no_flash_attn = unwrap(kwargs.get("no_flash_attention"), False) # low_mem is currently broken in exllamav2. Don't use it until it's fixed. """