Update README.md

README.md

@@ -15,7 +15,6 @@ cd MemoryLLM
 Then simply use the following code to load the model:
 ```python
 from modeling_memoryllm import MemoryLLM
-from configuration_memoryllm import MemoryLLMConfig
 from transformers import AutoTokenizer
 model = MemoryLLM.from_pretrained("YuWangX/memoryllm-8b-chat")
 tokenizer = AutoTokenizer.from_pretrained("YuWangX/memoryllm-8b-chat")
@@ -29,7 +28,9 @@ Inject a piece of context into the model using the following script:
 model = model.cuda()
 
 # Self-Update with the new context
-ctx = "David likes eating apples."
+ctx = "Last week, John had a wonderful picnic with David. During their conversation, David mentioned multiple times that he likes eating apples. Though he didn't mention any other fruits, John says he can infer that David also like bananas."
+
+# please make sure the context to inject into the memory is larger than 16 tokens, this is the hard minimum when training the model. The memory will be disturbed when less than 16 tokens are injected into the memory. 
 model.inject_memory(tokenizer(ctx, return_tensors='pt', add_special_tokens=False).input_ids.cuda(), update_memory=True)
 
 # Generation