From 198e6179efa60f27f7e44a4e39c4103c1aa4fe0e Mon Sep 17 00:00:00 2001 From: Florian Zimmermeister Date: Tue, 11 Jul 2023 18:36:04 +0200 Subject: [PATCH] Update causal_lm.py --- server/text_generation_server/models/causal_lm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/models/causal_lm.py b/server/text_generation_server/models/causal_lm.py index cbdf48083..a58f912f5 100644 --- a/server/text_generation_server/models/causal_lm.py +++ b/server/text_generation_server/models/causal_lm.py @@ -481,7 +481,7 @@ class CausalLM(Model): device_map="auto" if torch.cuda.is_available() and torch.cuda.device_count() > 1 else None, - load_in_8bit=quantize == "bitsandbytes", + load_in_4bit=quantize == "bitsandbytes", trust_remote_code=trust_remote_code, ) if torch.cuda.is_available() and torch.cuda.device_count() == 1: