Update README.md

README.md

@@ -39,6 +39,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="mps", # Change mps if not MacOS
     torch_dtype=torch.float32,  # try float16 for M1 chip
     trust_remote_code=True,
+    attn_implementation="eager", # without flash_attn
 )
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 ```