Update model.py

model.py

@@ -9,7 +9,7 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
 model_id = "CohereForAI/c4ai-command-r-v01-4bit"
 tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir=hf_cache_folder)
-model = AutoModelForCausalLM.from_pretrained(model_id, cache_dir=hf_cache_folder).to(device)
+model = AutoModelForCausalLM.from_pretrained(model_id, cache_dir=hf_cache_folder, device_map="auto")
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>