LLamaRecipes/end-to-end-use-cases/RAFT-Chatbot/raft_eval_config.yaml

eval_prompt_template: >
  <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a AI assistant that skilled in answering questions related to Llama language models,
  which includes LLama, Llama2, Meta Llama3, Code Llama, Meta Llama Guard 1,	Meta Llama Guard 2,
  Below is a question from a llama user, please the answer it with best of your knowledge,
  The returned answer should be no more than 60 words. Please return the answers in text directly without any special tokens.<|eot_id|>
  <|start_header_id|>user<|end_header_id|>
  Question:{question} \n <|eot_id|><|start_header_id|>assistant<|end_header_id|>
judge_prompt_template: >
    <|begin_of_text|><|start_header_id|>system<|end_header_id|>You have been provided with a question, a teacher's answer and a student's answer below.
    Given that question, you need to score the how good the student answer is compare to
    the teacher's answer. If the student's answer is correct based on the teacher's answer, then return YES, else return NO.
    Here are the grade criteria to follow:
    1. Review it carefully to make sure that the keywords and numerical values are exactly the same.
    2. Ensure that the student answer does not contain any conflicting statements.
    3. It is OK if the student answer contains more information than the ground truth answer, as long as it is factually accurate relative to the  ground truth answer.
    YES means that the student's answer meets all of the criteria.
    NO means that the student's answer does not meet all of the criteria. This is the lowest possible score you can give.
    Only respond with "YES" or "NO", do not respond with anything else.<|eot_id|>
    <|start_header_id|>user<|end_header_id|>
    Question: {question} \n Teacher's Answer: {gold} \n Student's Answer: {prediction} <|eot_id|><|start_header_id|>assistant<|end_header_id|>
RAG_prompt_template: >
  <|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful chatbot who can provide an answer to every questions from the user given a relevant context.<|eot_id|>
  <|start_header_id|>user<|end_header_id|>
  Question: {question}\nContext: {context}\n
  Answer this question using the information given by multiple documents in the context above. Here are the things to pay attention to:
  - The context contains many documents, each document starts with <DOCUMENT> and ends </DOCUMENT>.
  - First provide step-by-step reasoning on how to answer the question.
  - In the reasoning, if you need to copy paste some sentences from the context, include them in ##begin_quote## and ##end_quote##. This would mean that things outside of ##begin_quote## and ##end_quote## are not directly copy paste from the context.
  - End your response with final answer in the form <ANSWER>: $answer, the answer should less than 60 words.
  You MUST begin your final answer with the tag "<ANSWER>:". <|eot_id|><|start_header_id|>assistant<|end_header_id|>
eval_file: "./eval_llama.json"

model_name: "raft-8b"

data_dir: "./data"

rag_topk: 5