Update example to CCO

README.md

@@ -81,7 +81,7 @@ pipe = pipeline("text-generation", model="dataeaze/dataeaze-RegLLM-microsoft_phi
 
 pipe.tokenizer.pad_token = pipe.tokenizer.eos_token
 
-result = pipe(f"Instruct: Are there specific categories of ECBs with different MAMP requirements?",
+result = pipe(f"What are the skills that a CCO should have?",
               max_new_tokens=256,
               do_sample=True,
               temperature=0.1,
@@ -95,25 +95,24 @@ print(result)
 ## Sample Output
 
 ### Question
-Are there specific categories of ECBs with different MAMP requirements?
+What are the skills that a CCO should have?
 
 ### RegLLM respose
 
 ```
-Instruct: Are there specific categories of ECBs with different MAMP requirements?
-Output: Yes, there are various categories of ECBs, each with its own set of MAMP requirements.
-These categories may include infrastructure, commercial real estate, and other specific categories as defined by relevant regulations.
-The specific MAMP requirements for each category may vary, and banks must adhere to these requirements when extending ECBs.
+Instruct: What are the skills that a CCO should have?
+Output: The skills that a CCO should have include leadership, communication, and a strong understanding of compliance.
+They should also be able to work effectively with other departments and have a good track record of compliance.
 ```
 
 ### GPT-4 response
 <table>
   <tr style="border-spacing: 5px;">
     <td>
-<img src="chatgpt_ecb_1.png" alt="gpt-4-respnse" width="500" />
+<img src="chatgpt_cco_1.png" alt="gpt-4-respnse" width="500" />
     </td>
     <td>
-<img src="chatgpt_ecb_2.png" alt="gpt-4-respnse" width="500" />
+<img src="chatgpt_cco_2.png" alt="gpt-4-respnse" width="500" />
     </td>
   </tr>
 </table>
@@ -122,15 +121,15 @@ The specific MAMP requirements for each category may vary, and banks must adhere
 ### Reference 
 
 For evalating truthfulness / hallucination of this response, refer to RBI notification
-[RBI/FED/2018-19/67
-FED Master Direction No.5/2018-19](https://rbidocs.rbi.org.in/rdocs/notification/PDFs/5MD2603201979CA1390E9E546869B2A9A92614DEDBF.PDF) (page 9)
+[RBI/2022-23/24
+Ref.No.DoS.CO.PPG./SEC.01/11.01.005/2022-23](https://rbidocs.rbi.org.in/rdocs/Notification/PDFs/NT244C25EB0BBB1E4F91AEB101D425EA639A.PDF) (page 8)
 
 Screenshot below
 
-<img src="rbi_gold_answer_ecb.png" alt="rbi-gold-answer" width="500"/>
+<img src="CCO_Skills.png" alt="rbi-gold-answer" width="500"/>
 
 
-As you can see, RegLLM has identified the frequency of IRRBB policies, while GPT-4 provides a more general response.
+As you can see, RegLLM has identified CCO has identified Chief Compliance Officer, while GPT-4 (Copilot) identifies CCO has Chief Commercial Officer.
 Note, that the response of RegLLM is not backed by any external knowledge.
 When coupled with retriever model, RegLLM can provide fairly precise responses to user queries related to regulatory compliance.