evalscope 0.16.2__py3-none-any.whl → 0.17.0__py3-none-any.whl

evalscope/registry/data/qa_browser/category_mapping.yaml

@@ -1,10 +0,0 @@
-文本生成: ['写作', '续写生成', '通用写作', '应用文写作', '头脑风暴', '开放对话', '角色扮演']
-文本理解:
-  ['文本点评', '文本摘要', '润色/纠错', '文本分类', '情感分析', '信息抽取', '文本聚类', '序列处理']
-知识问答: ['百科知识问答']
-数学解题: ['数学解题']
-逻辑推理: ['逻辑推理', '阅读理解']
-CODING: ['CODING', '表格处理']
-翻译: ['翻译']
-安全风险: ['有伤害性']
-其他: ['*']

evalscope/registry/data/question.jsonl

@@ -1,80 +0,0 @@
-{"question_id": 1, "text": "How can I improve my time management skills?", "category": "generic"}
-{"question_id": 2, "text": "What are the most effective ways to deal with stress?", "category": "generic"}
-{"question_id": 3, "text": "What are the main differences between Python and JavaScript programming languages?", "category": "generic"}
-{"question_id": 4, "text": "How can I increase my productivity while working from home?", "category": "generic"}
-{"question_id": 5, "text": "Can you explain the basics of quantum computing?", "category": "generic"}
-{"question_id": 6, "text": "What are the differences between plant-based and animal-based protein sources?", "category": "generic"}
-{"question_id": 7, "text": "How can I develop my critical thinking skills?", "category": "generic"}
-{"question_id": 8, "text": "What are the major challenges faced by the education sector today?", "category": "generic"}
-{"question_id": 9, "text": "What are the primary factors that influence consumer behavior?", "category": "generic"}
-{"question_id": 10, "text": "What are the most effective strategies for conflict resolution in the workplace?", "category": "generic"}
-{"question_id": 11, "text": "What are some potential implications of using a single-use plastic bottle versus a reusable bottle on both the environment and human health?", "category": "knowledge"}
-{"question_id": 12, "text": "What factors would you consider when designing an inclusive and accessible public transportation system?", "category": "knowledge"}
-{"question_id": 13, "text": "How can governments utilize fiscal and monetary policies to combat economic recessions?", "category": "knowledge"}
-{"question_id": 14, "text": "How do language and cultural barriers affect the way people communicate and form relationships in multicultural societies?", "category": "knowledge"}
-{"question_id": 15, "text": "Describe a scenario where artificial intelligence could be used to improve the quality and efficiency of healthcare delivery.", "category": "knowledge"}
-{"question_id": 16, "text": "Explain the process of gene editing using CRISPR-Cas9 technology, and discuss its potential applications and ethical implications.", "category": "knowledge"}
-{"question_id": 17, "text": "How do vaccinations work to protect individuals and communities from infectious diseases, and what is herd immunity?", "category": "knowledge"}
-{"question_id": 18, "text": "How do social media platforms influence the way people consume and share news, and what are the potential implications for the spread of misinformation?", "category": "knowledge"}
-{"question_id": 19, "text": "How do cultural, social, and economic factors influence people's food choices, and how can this knowledge be used to promote healthier diets?", "category": "knowledge"}
-{"question_id": 20, "text": "Explain the process of natural selection and how it contributes to the evolution and adaptation of species.", "category": "knowledge"}
-{"question_id": 21, "text": "How would you introduce yourself as a medieval knight at a royal banquet?", "category": "roleplay"}
-{"question_id": 22, "text": "As a pirate captain, what would you say to your crew to motivate them to search for hidden treasure?", "category": "roleplay"}
-{"question_id": 23, "text": "If you were a Shakespearean character, how would you declare your love for someone in a soliloquy?", "category": "roleplay"}
-{"question_id": 24, "text": "As a superhero, how would you explain your origin story to a curious child?", "category": "roleplay"}
-{"question_id": 25, "text": "Imagine you are a time traveler from the year 3000. What technological advancements would you tell people about?", "category": "roleplay"}
-{"question_id": 26, "text": "As a sports commentator, describe the winning play in the final seconds of a championship game.", "category": "roleplay"}
-{"question_id": 27, "text": "Pretend to be a world-famous chef. How would you describe your signature dish to a panel of judges?", "category": "roleplay"}
-{"question_id": 28, "text": "You are a mountain climber reaching the summit of Mount Everest. Describe your emotions and the view from the top.", "category": "roleplay"}
-{"question_id": 29, "text": "As a space colonist on Mars, describe your daily life and the challenges you face living on another planet.", "category": "roleplay"}
-{"question_id": 30, "text": "Pretend to be a character in a post-apocalyptic world. Describe how you survive and the allies you encounter.", "category": "roleplay"}
-{"question_id": 31, "text": "How can you determine if a restaurant is popular among locals or mainly attracts tourists, and why might this information be useful?", "category": "common-sense"}
-{"question_id": 32, "text": "What are some subtle clues that suggest someone is pretending to understand a topic or conversation when they are actually confused or uninformed?", "category": "common-sense"}
-{"question_id": 33, "text": "Why might someone choose to use a paper map or ask for directions instead of relying on a GPS device or smartphone app?", "category": "common-sense"}
-{"question_id": 34, "text": "How can you determine if a person is genuinely interested in a conversation or simply being polite?", "category": "common-sense"}
-{"question_id": 35, "text": "Why might someone prefer to shop at a small, locally-owned business instead of a large chain store, even if the prices are higher?", "category": "common-sense"}
-{"question_id": 36, "text": "How can you assess the credibility of a source of information, such as a news article or blog post, without relying solely on the reputation of the author or publisher?", "category": "common-sense"}
-{"question_id": 37, "text": "Why do some people enjoy the sensation of being scared, such as by watching horror movies or going on roller coasters, while others avoid these experiences?", "category": "common-sense"}
-{"question_id": 38, "text": "How can observing the behavior of other people in a social situation provide clues about cultural norms and expectations?", "category": "common-sense"}
-{"question_id": 39, "text": "Do we have a moral obligation to explore space, or should we focus on solving Earth's problems first?", "category": "common-sense"}
-{"question_id": 40, "text": "In a world where automation is becoming increasingly prevalent, is it more important to prioritize job creation or technological progress?", "category": "common-sense"}
-{"question_id": 41, "text": "How many times does the average human blink in a lifetime? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 42, "text": "How many atoms are in a grain of salt? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 43, "text": "How many lightning strikes occur on Earth each day? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 44, "text": "How many balloons would it take to lift a house like in the movie \"Up\"? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 45, "text": "How many text messages are sent globally in a minute? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 46, "text": "How many words are spoken daily on Earth? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 47, "text": "How many snowflakes fall during a typical winter? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 48, "text": "How many pages are in all the books ever written? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 49, "text": "How many times has the Earth orbited the Sun since the beginning of life? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 50, "text": "How many songs have been recorded throughout history? Try to explain your answer. Your explanation should take the reader through your reasoning step-by-step.", "category": "fermi"}
-{"question_id": 51, "text": "What if the Internet had been invented during the Renaissance period?", "category": "counterfactual"}
-{"question_id": 52, "text": "What if the Aztecs had successfully repelled the Spanish conquistadors?", "category": "counterfactual"}
-{"question_id": 53, "text": "What if the Black Death had not occurred in the 14th century?", "category": "counterfactual"}
-{"question_id": 54, "text": "What if Isaac Newton had focused on biology instead of physics?", "category": "counterfactual"}
-{"question_id": 55, "text": "What if the Beatles had never formed as a band?", "category": "counterfactual"}
-{"question_id": 56, "text": "What if Alan Turing had not cracked the Enigma code during World War II?", "category": "counterfactual"}
-{"question_id": 57, "text": "What if the Suez Canal had never been constructed?", "category": "counterfactual"}
-{"question_id": 58, "text": "What if the Maya civilization had never mysteriously collapsed?", "category": "counterfactual"}
-{"question_id": 59, "text": "What if Christopher Columbus had not discovered the Americas?", "category": "counterfactual"}
-{"question_id": 60, "text": "What if Vincent van Gogh had been a successful artist during his lifetime?", "category": "counterfactual"}
-{"question_id": 61, "text": "Develop a C++ program that reads a text file line by line and counts the number of occurrences of a specific word in the file.", "category": "coding"}
-{"question_id": 62, "text": "Implement a Python function to find the longest common subsequence of two input strings using dynamic programming.", "category": "coding"}
-{"question_id": 63, "text": "Implement a regular expression in Python to validate an email address.", "category": "coding"}
-{"question_id": 64, "text": "Write a program to find the nth Fibonacci number using dynamic programming.", "category": "coding"}
-{"question_id": 65, "text": "Implement a binary search algorithm to find a specific element in a sorted array.", "category": "coding"}
-{"question_id": 66, "text": "Implement a queue data structure using two stacks in Python.", "category": "coding"}
-{"question_id": 67, "text": "Implement a program to find the common elements in two arrays without using any extra data structures.", "category": "coding"}
-{"question_id": 68, "text": "Given that f(x) = 5x^3 - 2x + 3, find the value of f(2).", "category": "math"}
-{"question_id": 69, "text": "Solve for x in the equation 3x + 10 = 5(x - 2).", "category": "math"}
-{"question_id": 70, "text": "If the endpoints of a line segment are (2, -2) and (10, 4), what is the length of the segment?", "category": "math"}
-{"question_id": 71, "text": "Can you help me write a formal email to a potential business partner proposing a joint venture?", "category": "writing"}
-{"question_id": 72, "text": "Can you help me write a resignation letter to my current employer, while leaving on good terms and expressing gratitude for the opportunities provided?", "category": "writing"}
-{"question_id": 73, "text": "Use an appropriate format to structure a formal letter of recommendation for a student applying to a prestigious graduate program in computer science.", "category": "writing"}
-{"question_id": 74, "text": "Write a compelling product launch announcement email to inform our customers of our new software solution.", "category": "writing"}
-{"question_id": 75, "text": "Draft an apology email to a customer who experienced a delay in their order, and provide reassurance that the issue has been resolved.", "category": "writing"}
-{"question_id": 76, "text": "Write a script for a YouTube video exploring the history and cultural significance of jazz.", "category": "writing"}
-{"question_id": 77, "text": "Compose an engaging travel blog post about a recent trip to Hawaii, highlighting cultural experiences and must-see attractions.", "category": "writing"}
-{"question_id": 78, "text": "Write a captivating movie review for a recently released science fiction film, discussing its plot, characters, and special effects.", "category": "writing"}
-{"question_id": 79, "text": "Structure a podcast script for an episode discussing the influence of streaming platforms on the music industry.", "category": "writing"}
-{"question_id": 80, "text": "Write a symphony concert review, discussing the orchestra's performance and overall audience experience.", "category": "writing"}

evalscope/registry/tasks/arc.yaml

@@ -1,28 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args:
-  arc:
-    prompt_template: 'The following are multiple choice questions, please output correct answer in the form of A or B or C or D, do not output explanation:'
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - arc
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/bbh.yaml

@@ -1,26 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - bbh
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/bbh_mini.yaml

@@ -1,26 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {'bbh': {'subset_list': ['temporal_sequences', 'multistep_arithmetic_two']}}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - bbh
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/ceval.yaml

@@ -1,27 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - ceval
-outputs: null    # structure: configs, logs, predictions, reviews, reports # TODO: need to parse
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/ceval_mini.yaml

@@ -1,26 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {'ceval': {'subset_list': ['computer_network', 'operating_system']}}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - ceval
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/cmmlu.yaml

@@ -1,27 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - cmmlu
-outputs: null    # structure: configs, logs, predictions, reviews, reports # TODO: need to parse
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml

@@ -1,28 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: v1.0.0
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - arc
-  - gsm8k
-outputs: ./outputs/eval_qwen-7b-chat_v100    # Directory to save the outputs, structure: logs, predictions, reviews, reports
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: 10

evalscope/registry/tasks/general_qa.yaml

@@ -1,27 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: true
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - general_qa
-outputs: null    # structure: configs, logs, predictions, reviews, reports # TODO: need to parse
-use_cache: false
-stage: all
-dataset_hub: Local    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/gsm8k.yaml

@@ -1,29 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args:
-  gsm8k:
-    few_shot_num: 0
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - gsm8k
-outputs: null    # structure: configs, logs, predictions, reviews, reports # TODO: need to parse
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/mmlu.yaml

@@ -1,29 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args:
-  mmlu:
-    few_shot_num: 0
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - mmlu
-outputs: null    # structure: configs, logs, predictions, reviews, reports # TODO: need to parse
-use_cache: true
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/registry/tasks/mmlu_mini.yaml

@@ -1,27 +0,0 @@
-model_args:    # model args should be followed by benchmark requirements
-  revision: master
-  precision: torch.float16
-  device_map: auto
-#  model_name_or_path: qwen/qwen-7b-chat
-generation_config:
-  temperature: 0.3
-  max_length: 2048
-  max_new_tokens: 512
-  top_k: 50
-  top_p: 0.85
-  do_sample: false
-  num_beams: 1
-  repetition_penalty: 1.0
-#  eos_token_id: null
-#  pad_token_id: null
-dataset_args: {'mmlu': {'subset_list': ['high_school_european_history', 'business_ethics']}}
-dry_run: false
-model: null   # Note: to be implemented as CustomModel
-eval_type: custom
-datasets:
-  - mmlu
-outputs: null    # structure: configs, logs, predictions, reviews, reports # TODO: need to parse
-use_cache: false
-stage: all
-dataset_hub: modelscope    # `Local` or `ModelScope`
-limit: null

evalscope/run_arena.py

@@ -1,202 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.
-# flake8: noqa
-
-import argparse
-import os
-import torch
-from modelscope.utils.hf_util import GenerationConfig
-from pathlib import Path
-from tqdm import tqdm
-
-from evalscope.constants import EvalConfigKeys
-from evalscope.evaluator.rating_eval import RatingEvaluate
-from evalscope.models import ChatGenerationModelAdapter
-from evalscope.utils import get_obj_from_cfg
-from evalscope.utils.io_utils import dump_jsonl_data, jsonl_to_list, yaml_to_dict
-from evalscope.utils.logger import get_logger
-
-logger = get_logger()
-
-WORK_DIR = Path(__file__).absolute().parent
-
-
-class ArenaWorkflow:
-
-    def __init__(self, cfg_file: str, **kwargs):
-
-        self.cfg_dict = yaml_to_dict(os.path.join(WORK_DIR, cfg_file))
-        logger.info(f'**Arena Config: {self.cfg_dict}')
-
-        self.question_file: str = os.path.join(WORK_DIR, self.cfg_dict.get('question_file'))
-        self.answers_gen: dict = self.cfg_dict.get('answers_gen', {})
-        self.reviews_gen: dict = self.cfg_dict.get('reviews_gen', {})
-        self.reviewer_cfg: dict = ArenaWorkflow._get_obj_from_cfg(self.reviews_gen.get('reviewer', {}))
-
-        self.prompt_file = os.path.join(WORK_DIR, self.reviews_gen.get('prompt_file'))
-        self.review_file = os.path.join(WORK_DIR, self.reviews_gen.get('review_file'))
-
-        self.rating_gen: dict = self.cfg_dict.get('rating_gen', {})
-        self.report_file: str = os.path.join(WORK_DIR, self.rating_gen.get('report_file'))
-
-    @staticmethod
-    def _get_obj_from_cfg(obj_cfg: dict):
-        cls_ref = obj_cfg.get(EvalConfigKeys.CLASS_REF, None)
-        if not cls_ref:
-            logger.warning(f'Class reference is not specified in config: {obj_cfg}')
-            return obj_cfg
-
-        cls = get_obj_from_cfg(cls_ref)
-        obj_cfg[EvalConfigKeys.CLASS_REF] = cls
-
-        return obj_cfg
-
-    def _predict_answers(self, model_id_or_path: str, model_revision: str, precision: torch.dtype,
-                         generation_config: GenerationConfig, template_type: str) -> list:
-
-        # TODO: multi-task to be supported
-        model_adapter = ChatGenerationModelAdapter(
-            model_id=model_id_or_path,
-            model_revision=model_revision,
-            torch_dtype=precision,
-            generation_config=generation_config,
-            template_type=template_type)
-        res_list = []
-        questions_list = jsonl_to_list(self.question_file)
-        for data_d in tqdm(questions_list, total=len(questions_list), desc=f'Predicting(answers):'):
-            # {"question_id": 1, "text": "How can I improve my time management skills?", "category": "generic"}
-            text = data_d.get('text', None)
-            if not text:
-                logger.warning(f'Invalid question: {data_d}')
-                continue
-            prompt = f'Question: {text}\n\nAnswer:'
-            inputs = {'data': [prompt]}
-            res_d: dict = model_adapter.predict(inputs=inputs)
-            ans_text: str = res_d['choices'][0]['message']['content']
-
-            ans = {
-                'question_id': data_d['question_id'],
-                'text': data_d['text'],
-                'category': data_d['category'],
-                'model_id': model_id_or_path,
-                'metadata': {},
-                'answer': ans_text,
-            }
-            res_list.append(ans)
-
-        return res_list
-
-    def get_answers(self):
-        for model_name, cfg_d in self.answers_gen.items():
-            enable = cfg_d.get(EvalConfigKeys.ENABLE, True)
-            if not enable:
-                logger.warning(f'Skip model {model_name} because it is not enabled.')
-                continue
-
-            model_id_or_path = cfg_d.get(EvalConfigKeys.MODEL_ID_OR_PATH)
-            model_revision = cfg_d.get(EvalConfigKeys.MODEL_REVISION, None)
-            precision = cfg_d.get(EvalConfigKeys.PRECISION, torch.float16)
-            precision = eval(precision) if isinstance(precision, str) else precision
-            custom_generation_config = cfg_d.get(EvalConfigKeys.GENERATION_CONFIG, {})
-            custom_generation_config = GenerationConfig(**custom_generation_config)
-            ans_output_file = os.path.join(WORK_DIR, cfg_d.get(EvalConfigKeys.OUTPUT_FILE))
-            template_type = cfg_d.get(EvalConfigKeys.TEMPLATE_TYPE)
-
-            answers_list = self._predict_answers(
-                model_id_or_path=model_id_or_path,
-                model_revision=model_revision,
-                precision=precision,
-                generation_config=custom_generation_config,
-                template_type=template_type)
-
-            os.makedirs(os.path.dirname(ans_output_file), exist_ok=True)
-            dump_jsonl_data(answers_list, ans_output_file)
-            logger.info(f'Answers generated by model {model_name} and saved to {ans_output_file}')
-
-    def get_reviews(self, dry_run: bool = False):
-        enable = self.reviews_gen.get(EvalConfigKeys.ENABLE, True)
-        if enable:
-            reviewer_cls = self.reviewer_cfg.get(EvalConfigKeys.CLASS_REF)
-            if not reviewer_cls:
-                logger.warning('Skip reviews generation because class reference is not specified.')
-                return
-            reviewer_args = self.reviewer_cfg.get(EvalConfigKeys.CLASS_ARGS, {})
-            target_answers = self.reviews_gen.get('target_answers')
-            if target_answers is None:
-                # Get all answers from answers_gen config if target_answers is None
-                target_answers = [item[EvalConfigKeys.OUTPUT_FILE] for item in self.answers_gen.values()]
-            target_answers = [os.path.join(WORK_DIR, item) for item in target_answers]
-            target_answers = [file_path for file_path in target_answers if os.path.exists(file_path)]
-
-            baseline_file = self.reviews_gen.get('baseline_file', None)
-            if baseline_file:
-                baseline_file = os.path.join(WORK_DIR, baseline_file)
-
-            reference_file = self.reviews_gen.get('reference_file', None)
-            if reference_file:
-                reference_file = os.path.join(WORK_DIR, reference_file)
-
-            cache_file = self.reviews_gen.get('cache_file', None)
-            if cache_file:
-                cache_file = os.path.join(WORK_DIR, cache_file)
-
-            input_kwargs = dict(
-                prompt_file=self.prompt_file,
-                answer_file_list=target_answers,
-                review_result_file=self.review_file,
-                baseline_file=baseline_file,
-                reference_file=reference_file,
-                reviewer_args=reviewer_args,
-                cache_file=cache_file)
-
-            reviewer_obj = reviewer_cls(**input_kwargs)
-            reviewer_obj.run(dry_run=dry_run)
-            logger.info(f'Reviews with generated by reviewer and saved to {self.review_file}')
-
-        else:
-            logger.warning('Skip reviews generation because it is not enabled.')
-
-    def get_rating_results(self):
-        enable = self.rating_gen.get(EvalConfigKeys.ENABLE, True)
-        if enable:
-            report_file = os.path.join(WORK_DIR, self.rating_gen.get('report_file'))
-            metrics = self.rating_gen.get('metrics', ['elo'])
-            baseline_model = self.rating_gen.get('baseline_model') if metrics[0] == 'pairwise' else None
-            ae = RatingEvaluate(metrics=metrics, baseline_model=baseline_model)
-            res_list = ae.run(self.review_file)
-            rating_df = res_list[0]
-            logger.info(f'Rating results:\n{rating_df.to_csv()}')
-            os.makedirs(os.path.dirname(report_file), exist_ok=True)
-            rating_df.to_csv(report_file, index=True)
-            logger.info(f'Rating results are saved to {report_file}')
-        else:
-            logger.warning('Skip rating because it is not enabled.')
-
-    def run(self, dry_run: bool = False):
-
-        # Get all answers
-        self.get_answers()
-
-        # Get all reviews
-        self.get_reviews(dry_run=dry_run)
-
-        # Get rating results
-        self.get_rating_results()
-
-        logger.info('*** Arena workflow is finished. ***')
-
-
-def main():
-
-    # Usage: python evalscope/run_arena.py -c /path/to/xxx_cfg_arena.yaml
-
-    parser = argparse.ArgumentParser(description='LLMs evaluations with arena mode.')
-    parser.add_argument('-c', '--cfg-file', required=True)
-    parser.add_argument('--dry-run', action='store_true', default=False)
-    args = parser.parse_args()
-
-    arena_workflow = ArenaWorkflow(cfg_file=args.cfg_file)
-    arena_workflow.run(dry_run=args.dry_run)
-
-
-if __name__ == '__main__':
-    main()