update HuMatchingFIB

examples/eval_OpenHuEval_HuStandardFIB.py

@@ -0,0 +1,13 @@
+from mmengine.config import read_base
+
+with read_base():
+    from opencompass.configs.datasets.OpenHuEval.HuStandardFIB.HuStandardFIB import hu_standard_fib_datasets
+
+    from opencompass.configs.models.openai.gpt_4o_mini_20240718 import models as gpt_4o_mini_20240718_model
+    from opencompass.configs.models.qwen2_5.lmdeploy_qwen2_5_7b_instruct import models as lmdeploy_qwen2_5_7b_instruct_model
+    from opencompass.configs.models.hf_internlm.lmdeploy_internlm3_8b_instruct import models as lmdeploy_internlm3_8b_instruct_model
+    # from opencompass.configs.models.qwq.lmdeploy_qwq_32b_preview import models as lmdeploy_qwq_32b_preview_model
+
+datasets = hu_standard_fib_datasets
+models = sum([v for k, v in locals().items() if k.endswith('_model')], [])
+work_dir = './outputs/' + __file__.split('/')[-1].split('.')[0] + '/' # do NOT modify this line, yapf: disable, pylint: disable

opencompass/configs/datasets/OpenHuEval/HuStandardFIB/HuStandardFIB.py

@@ -6,27 +6,23 @@ from opencompass.openicl.icl_inferencer import GenInferencer
 from opencompass.datasets.OpenHuEval.HuStandardFIB import HuStandardFIBDataset, HuStandardFIBEvaluator
 
 with read_base():
-    from .HuStandardFIB_setting import INSTRUCTIONS, DATASET_PATH
+    from .HuStandardFIB_setting import INSTRUCTION, DATA_PATH, DATA_VERSION
 
-ALL_LANGUAGES = ['hu']
-PROMPT_VERSION = INSTRUCTIONS['version']
+instruction = INSTRUCTION['prompt_template']
+prompt_version = INSTRUCTION['version']
 
-FIB2_reader_cfg = dict(input_columns=['question', 'subject'],
+hu_standard_fib_reader_cfg = dict(input_columns=['question', 'subject'],
                                   output_column='reference')
 
-FIB2_datasets = []
-for lan in ALL_LANGUAGES:
-    instruction = INSTRUCTIONS[lan]
-    FIB2_infer_cfg = dict(
+hu_standard_fib_datasets = []
+
+hu_standard_fib_infer_cfg = dict(
     prompt_template=dict(
         type=PromptTemplate,
         template=dict(
             begin='</E>',
             round=[
-                    dict(
-                        role='HUMAN',
-                        prompt=instruction
-                    ),
+                dict(role='HUMAN', prompt=instruction),
             ],
         ),
         ice_token='</E>',
@@ -35,16 +31,14 @@ for lan in ALL_LANGUAGES:
     inferencer=dict(type=GenInferencer),
 )
 
-    FIB2_eval_cfg = dict(evaluator=dict(type=HuStandardFIBEvaluator))
+hu_standard_fib_eval_cfg = dict(evaluator=dict(type=HuStandardFIBEvaluator))
 
-    FIB2_datasets.append(
+hu_standard_fib_datasets.append(
     dict(
-            abbr=f'HuStandardFIB-{lan}-1shot-{PROMPT_VERSION}',
+        abbr=f'hu_standard_fib_{DATA_VERSION}-prompt_{prompt_version}',
         type=HuStandardFIBDataset,
-            path=DATASET_PATH,
-            lan=lan,
-            reader_cfg=FIB2_reader_cfg,
-            infer_cfg=FIB2_infer_cfg,
-            eval_cfg=FIB2_eval_cfg,
-        )
-    )
+        filepath=DATA_PATH,
+        reader_cfg=hu_standard_fib_reader_cfg,
+        infer_cfg=hu_standard_fib_infer_cfg,
+        eval_cfg=hu_standard_fib_eval_cfg,
+    ))

opencompass/configs/datasets/OpenHuEval/HuStandardFIB/HuStandardFIB_setting.py

@@ -1,15 +1,27 @@
-INSTRUCTIONS = {
-    'hu': """The following question is in hungarian language on {subject}, please read the question, and try to fill in the blank in the sub question list. Please organize the answer in a list. An example:
+INSTRUCTION = {
+    'prompt_template':
+    """The following questions are in Hungarian language on {hu_specific_dim}, please read the questions, and try to fill in the blanks in the question list. Please organize the answer in a list. An example:
 {
-        "q_main": "Írd be a megfelelő meghatározás mellé a fogalmat!",
-        "q_sub": ["A.A szerzetesi közösségek szabályzatának elnevezése latinul: #0#", "B.Az első ún. kolduló rend: #1#", "C.A szerzetesek által kézzel másolt mű: #2#", "D.Papi nőtlenség: #3#", "E.A pápát megválasztó egyházi méltóságok: #4#", "F.A bencés rend megújítása ebben a kolostorban kezdődött a 10. században: #5#"],
-        "formatted_std_ans": ["#0#regula", "#1#ferencesrend;ferences", "#2#kódex", "#3#cölibátus", "#4#bíborosok;bíboros", "#5#Cluny"]
+    "instruction": "Írd be a megfelelő meghatározás mellé a fogalmat!",
+    "questions": ["A.A szerzetesi közösségek szabályzatának elnevezése latinul: #0#", "B.Az első ún. kolduló rend: #1#", "C.A szerzetesek által kézzel másolt mű: #2#", "D.Papi nőtlenség: #3#", "E.A pápát megválasztó egyházi méltóságok: #4#", "F.A bencés rend megújítása ebben a kolostorban kezdődött a 10. században: #5#"],
+}
+The answers are:
+{
+    "answers": ["#0#regula", "#1#ferencesrend", "#2#kódex", "#3#cölibátus", "#4#bíborosok", "#5#Cluny"]
+}
+Now try to answer the following questions, your response should be in a JSON format. Contain the "answers" like the case given above.
+The questions are:
+{
+    "instruction": {instruction},
+    "questions": {questions},
 }
-    Now try to answer the following question, your response should be in a JSON format. Contain the std_ans like the case given above.
-    The question is: {question}.
 """,
-    'version':'V1',
-    'description': 'Initial version, using 1shot, incontext, #0# as place holder, output in JSON format',
+    'version':
+    'V1',
+    'description':
+    'Initial version, using 1shot, incontext, #0# as place holder, output in JSON format',
 }
 
-DATASET_PATH = "/mnt/hwfile/opendatalab/weixingjian/test/test2/"
+OpenHuEval_Path = '/mnt/hwfile/opendatalab/wj/proj/polyglot_24July/OpenHuEval'
+DATA_VERSION = '250126'
+DATA_PATH = f'{OpenHuEval_Path}/data/HuStandardFIB/HuStandardFIB_{DATA_VERSION}/HuStandardFIB.jsonl'

opencompass/datasets/OpenHuEval/HuStandardFIB.py

@@ -4,21 +4,20 @@ import re
 
 from datasets import Dataset, DatasetDict
 from fuzzywuzzy import fuzz
+
 from opencompass.openicl.icl_evaluator import BaseEvaluator
+
 from ..base import BaseDataset
 
 
 class HuStandardFIBDataset(BaseDataset):
 
     @staticmethod
-    def load(**kwargs):
-        path = kwargs.get('path', None)
-        # lan = kwargs.get('lan', None)
+    def load(filepath):
+        assert os.path.isfile(filepath)
+        assert filepath.endswith('.jsonl')
         dataset = DatasetDict()
-        file_list = [os.path.join(path, file) for file in os.listdir(path)
-                     ]  # TODO only work for a single split.
-        f_path = file_list[0]
-        f = open(f_path, 'r', encoding='utf-8')
+        f = open(filepath, 'r', encoding='utf-8')
         lines = f.readlines()
         objs = []
 
@@ -29,11 +28,15 @@ class HuStandardFIBDataset(BaseDataset):
         out_dict_list = []
 
         for obj in objs:
-            question = dict(q_main=obj['q_main'],
-                            q_sub=obj['formatted_q_sub'])  # TODO
-            subject = obj['major']
+            instruction = obj['question']  # TODO: question -> instruction
+            questions = obj[
+                'question_sub']  # TODO: update question_sub -> questions
+            hu_specific_dim = obj['hu_specific_dim']
             tmp = obj
-            new_obj = dict(question=question, subject=subject, reference=tmp)
+            new_obj = dict(instruction=instruction,
+                           questions=questions,
+                           hu_specific_dim=hu_specific_dim,
+                           reference=tmp)
             out_dict_list.append(new_obj)
         dataset = Dataset.from_list(out_dict_list)
         return dataset
@@ -55,9 +58,8 @@ class HuStandardFIBEvaluator(BaseEvaluator):
                 zip(predictions, references, origin_prompt)):
             std_ans = [
                 re.sub(r'#\d+#', '', ans).split(';')
-                for ans in refer['formatted_std_ans']
-            ]  # Remove "#0#" and "#1#", then split
-            # refer['formatted_std_ans']
+                for ans in refer['answer']  # TODO: answer -> answers
+            ]  # Remove "#0#" and "#1#", then split refer['formatted_std_ans']
             model_ans = []
             pred = pred.strip()
             match = re.search(r'\{.*?\}', pred, re.DOTALL)
@@ -99,7 +101,7 @@ class HuStandardFIBEvaluator(BaseEvaluator):
             if to_end_flag:
                 model_ans = [
                     re.sub(r'#\d+#', '', ans).split(';')
-                    for ans in data.get('formatted_std_ans', [])
+                    for ans in data.get('answers', [])
                 ]  # Preprocess model_ans in the same way as std_ans
                 is_question_correct = True
                 for idx, ans_list in enumerate(std_ans):