Update answerability_prediction_lora/README.md

answerability_prediction_lora/README.md

@@ -33,7 +33,8 @@ To prompt the LoRA adapter to determine answerability, a special answerability r
 
 ## Quickstart Example
 
-While you can invoke the adapter directly, as outlined below, we highly recommend calling it through [granite-io](https://github.com/ibm-granite/granite-io), which wraps the model with a tailored I/O processor.
+While you can invoke the adapter directly, as outlined below, we highly recommend calling it through [granite-io](https://github.com/ibm-granite/granite-io), which wraps the model with a tailored I/O processor. 
+Before running the script, set the `LORA_NAME` parameter to the path of the directory that you downloaded the LoRA adapter. The download process is explained [here](https://huggingface.co/ibm-granite/granite-3.3-8b-rag-agent-lib#quickstart-example). 
 
 ```
 import  torch
@@ -45,7 +46,7 @@ device=torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
 ANSWERABILITY_PROMPT = "<|start_of_role|>answerability<|end_of_role|>"
 BASE_NAME = "ibm-granite/granite-3.3-8b-instruct"
-LORA_NAME = "ibm-granite/granite-3.3-8b-lora-rag-answerability-prediction"
+LORA_NAME = "PATH_TO_DOWNLOADED_DIRECTORY"
 
 tokenizer = AutoTokenizer.from_pretrained(BASE_NAME, padding_side='left',trust_remote_code=True)
 model_base = AutoModelForCausalLM.from_pretrained(BASE_NAME,device_map="auto")