update readme

README.md

@@ -2,7 +2,7 @@
 
 This repository contains a LLaMA-7B fine-tuned model on the [Standford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) cleaned version dataset.
 
-I used [LLaMA-7B-hf](decapoda-research/llama-7b-hf) as a base model
+⚠️ **I used [LLaMA-7B-hf](decapoda-research/llama-7b-hf) as a base model, so this model is for Research purpose only (See the [license](https://huggingface.co/decapoda-research/llama-7b-hf/blob/main/LICENSE))**
 
 # Usage
 
@@ -17,4 +17,9 @@ model = LlamaForCausalLM.from_pretrained(
     load_in_8bit=True,
     torch_dtype=torch.float16,
     device_map="auto",
-)
+)
+
+model.eval()
+if torch.__version__ >= "2":
+    model = torch.compile(model)
+```