From 78b1e83c3fc6762aa1253b8b8bf4508e698741ed Mon Sep 17 00:00:00 2001
From: AlexanderLavelle <73360008+AlexanderLavelle@users.noreply.github.com>
Date: Wed, 24 Apr 2024 19:56:11 -0400
Subject: [PATCH] quantized models don't have .to

ValueError: `.to` is not supported for `4-bit` or `8-bit` bitsandbytes models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`.
---
 swarms/models/huggingface.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/swarms/models/huggingface.py b/swarms/models/huggingface.py
index e459b251..993aa8cf 100644
--- a/swarms/models/huggingface.py
+++ b/swarms/models/huggingface.py
@@ -181,7 +181,7 @@ class HuggingfaceLLM(AbstractLLM):
                 quantization_config=bnb_config,
                 *args,
                 **kwargs,
-            ).to(self.device)
+            )
         else:
             self.model = AutoModelForCausalLM.from_pretrained(
                 self.model_id, *args, **kwargs