diff --git a/README.md b/README.md
index 75ec69f..6049440 100644
--- a/README.md
+++ b/README.md
@@ -198,7 +198,8 @@ model_name = "deepseek-ai/DeepSeek-V2"
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 # `max_memory` should be set based on your devices
 max_memory = {i: "75GB" for i in range(8)}
-model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16, max_memory=max_memory)
+# `device_map` cannot be set to `auto`
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="sequential", torch_dtype=torch.bfloat16, max_memory=max_memory, attn_implementation="eager")
 model.generation_config = GenerationConfig.from_pretrained(model_name)
 model.generation_config.pad_token_id = model.generation_config.eos_token_id
 
@@ -219,7 +220,8 @@ model_name = "deepseek-ai/DeepSeek-V2-Chat"
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 # `max_memory` should be set based on your devices
 max_memory = {i: "75GB" for i in range(8)}
-model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.bfloat16, max_memory=max_memory)
+# `device_map` cannot be set to `auto`
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="sequential", torch_dtype=torch.bfloat16, max_memory=max_memory, attn_implementation="eager")
 model.generation_config = GenerationConfig.from_pretrained(model_name)
 model.generation_config.pad_token_id = model.generation_config.eos_token_id