From d6649411c4b4079ff44852e853543224835a3f14 Mon Sep 17 00:00:00 2001 From: cdawg Date: Wed, 19 Jul 2023 17:43:49 +0200 Subject: [PATCH] Update quantize.py --- server/text_generation_server/utils/gptq/quantize.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/utils/gptq/quantize.py b/server/text_generation_server/utils/gptq/quantize.py index d182456f..5ec2d011 100644 --- a/server/text_generation_server/utils/gptq/quantize.py +++ b/server/text_generation_server/utils/gptq/quantize.py @@ -864,7 +864,7 @@ def quantize( ) with init_empty_weights(): - model = AutoModelForCausalLM.from_config(config, torch_dtype=torch.float16) + model = AutoModelForCausalLM.from_config(config, torch_dtype=torch.float16,trust_remote_code=trust_remote_code) model = model.eval() print("LOADED model")