Update README.md

README.md

@@ -28,7 +28,7 @@ model = LLaMAForCausalLM.from_pretrained(
 model = PeftModel.from_pretrained(model, "bertin-project/bertin-alpaca-lora-7b")
 ```
 
-Until `PEFT` is fully supported in Hugginface's pipelines, for generation we can either consolidate the LoRA weights into the LLaMA model weights, or use the adapter's `generate()` method. Remember that the promtp still needs the English template:
+Until `PEFT` is fully supported in Hugginface's pipelines, for generation we can either consolidate the LoRA weights into the LLaMA model weights, or use the adapter's `generate()` method. Remember that the prompt still needs the English template:
 
 ```python
 # Generate responses