Prasyarat

1. !pip3 install sagemaker
   !pip3 install -U pyarrow
   !pip3 install -U accelerate
   !pip3 install "ipywidgets>=8"
   !pip3 install jsonlines
   !pip install fmeval
   !pip3 install boto3==1.28.65
   import sagemaker

3. import glob
   
   # Check for fmeval wheel and built-in dataset
   if not glob.glob("crows-pairs_sample.jsonl"):
   print("ERROR - please make sure file exists: crows-pairs_sample.jsonl")
                       

4. from sagemaker.jumpstart.model import JumpStartModel
   
   model_id, model_version, = (
   "huggingface-llm-falcon-7b-instruct-bf16",
   "*",
   )

5. my_model = JumpStartModel(model_id=model_id)
   predictor = my_model.deploy()
   endpoint_name = predictor.endpoint_name

6. prompt = "London is the capital of"
   payload = {
   "inputs": prompt,
   "parameters": {
       "do_sample": True,
       "top_p": 0.9,
       "temperature": 0.8,
       "max_new_tokens": 1024,
       "decoder_input_details" : True,
       "details" : True
   },
   }

   • Default ke False.

   • Default ke 20.

   • Default ke False.

1. import fmeval
   from fmeval.data_loaders.data_config import DataConfig
   from fmeval.model_runners.sm_jumpstart_model_runner import JumpStartModelRunner
   from fmeval.constants import MIME_TYPE_JSONLINES
   from fmeval.eval_algorithms.prompt_stereotyping import PromptStereotyping, PROMPT_STEREOTYPING
   from fmeval.eval_algorithms import EvalAlgorithm

2. config = DataConfig(
   dataset_name="crows-pairs_sample",
   dataset_uri="crows-pairs_sample.jsonl",
   dataset_mime_type=MIME_TYPE_JSONLINES,
   sent_more_input_location="sent_more",
   sent_less_input_location="sent_less",
   category_location="bias_type",
   )

3. js_model_runner = JumpStartModelRunner(
   endpoint_name=endpoint_name,
   model_id=model_id,
   model_version=model_version,
   output='[0].generated_text',
   log_probability='[0].details.prefill[*].logprob',
   content_template='{"inputs": $prompt, "parameters":
   {"do_sample": true, "top_p": 0.9, "temperature": 0.8, "max_new_tokens": 1024,
   "decoder_input_details": true,"details": true}}',
   )

4. import os
   eval_dir = "results-eval-prompt-stereotyping"
   curr_dir = os.getcwd()
   eval_results_path = os.path.join(curr_dir, eval_dir) + "/"
   os.environ["EVAL_RESULTS_PATH"] = eval_results_path
   if os.path.exists(eval_results_path):
   print(f"Directory '{eval_results_path}' exists.")
   else:
   os.mkdir(eval_results_path)

5. os.environ["PARALLELIZATION_FACTOR"] = "1"

1. eval_algo = PromptStereotyping()

2. eval_output = eval_algo.evaluate(model=js_model_runner, dataset_config=config,
   prompt_template="$feature", save=True)

1. import json
   print(json.dumps(eval_output, default=vars, indent=4))
   

   [
   {
       "eval_name": "prompt_stereotyping",
       "dataset_name": "crows-pairs_sample",
       "dataset_scores": [
           {
               "name": "prompt_stereotyping",
               "value": 0.6666666666666666
           }
       ],
       "prompt_template": "$feature",
       "category_scores": [
           {
               "name": "disability",
               "scores": [
                   {
                       "name": "prompt_stereotyping",
                       "value": 0.5
                   }
               ]
           },
           ...
       ],
       "output_path": "/home/sagemaker-user/results-eval-prompt-stereotyping/prompt_stereotyping_crows-pairs_sample.jsonl",
       "error": null
   }
   ]

2. import pandas as pd
   data = []
   with open(os.path.join(eval_results_path,
   "prompt_stereotyping_crows-pairs_sample.jsonl"), "r") as file:
   for line in file:
   data.append(json.loads(line))
   df = pd.DataFrame(data)
   df['eval_algo'] = df['scores'].apply(lambda x: x[0]['name'])
   df['eval_score'] = df['scores'].apply(lambda x: x[0]['value'])
   df