add function to add both task and benchmark

lm_eval/tasks/__init__.py

@@ -45,6 +45,18 @@ def register_configurable_group(config: Dict[str, str]) -> int:
     task_list = [task for task in all_task_list if type(task) == str]
 
     for task_config in config_list:
+        # if "task" in task_config:
+        #     task = task_config["task"]
+        #     if task in GROUP_REGISTRY:
+        #         task_list = GROUP_REGISTRY[task]
+        #     elif task in TASK_REGISTRY:
+        #         task_list = [TASK_REGISTRY[task]]
+        
+        #     for _task in task_list:
+        #         task_config = {
+        #             **_task["CONFIG"],
+        #             **task_config
+        #         }
         var_configs = check_prompt_config(
             {
                 **task_config,
@@ -109,36 +121,40 @@ def include_task_folder(task_dir: str, register_task=True) -> None:
     Calling this function
     """
     for root, subdirs, file_list in os.walk(task_dir):
-        if (subdirs == [] or subdirs == ["__pycache__"]) and (len(file_list) > 0):
-            for f in file_list:
-                if f.endswith(".yaml"):
-                    yaml_path = os.path.join(root, f)
-                    try:
-                        config = utils.load_yaml_config(yaml_path)
-
-                        if register_task:
-                            all_configs = check_prompt_config(config)
-                            for config in all_configs:
-                                register_configurable_task(config)
-                        else:
-                            # If a `task` in config is a list,
-                            # that means it's a benchmark
-                            if type(config["task"]) == list:
-                                register_configurable_group(config)
-
-                    except Exception as error:
-                        eval_logger.warning(
-                            "Failed to load config in\n"
-                            f"                                 {yaml_path}\n"
-                            "                                 Config will not be added to registry\n"
-                            f"                                 Error: {error}"
-                        )
-
+        # if (subdirs == [] or subdirs == ["__pycache__"]) and (len(file_list) > 0):
+        for f in file_list:
+            if f.endswith(".yaml"):
+                yaml_path = os.path.join(root, f)
+                try:
+                    config = utils.load_yaml_config(yaml_path)
+
+                    if register_task:
+                        all_configs = check_prompt_config(config)
+                        for config in all_configs:
+                            register_configurable_task(config)
+                    else:
+                        # If a `task` in config is a list,
+                        # that means it's a benchmark
+                        if type(config["task"]) == list:
+                            register_configurable_group(config)
+
+                except Exception as error:
+                    eval_logger.warning(
+                        "Failed to load config in\n"
+                        f"                                 {yaml_path}\n"
+                        "                                 Config will not be added to registry\n"
+                        f"                                 Error: {error}"
+                    )
+
+
+def include_path(task_dir):
+    include_task_folder(task_dir)
+    # Register Benchmarks after all tasks have been added
+    include_task_folder(task_dir, register_task=False)
+    return 0
 
 task_dir = os.path.dirname(os.path.abspath(__file__)) + "/"
-include_task_folder(task_dir)
-# Register Benchmarks after all tasks have been added
-include_task_folder(task_dir, register_task=False)
+include_path(task_dir)
 
 
 def get_task(task_name, config):

lm_eval/tasks/benchmarks/flan/prompt_templates/flan_anli.yaml

-# Flan Prompt Templates
-prompts:
-  "template-0":
-    doc_to_text: "{{premise}}\n\nChoose your answer: based on the paragraph above can we conclude that \"{{hypothesis}}\"?\n\nOPTIONS:\n- Yes\n- It's impossible to say\n- No\nI think the answer is"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-1":
-    doc_to_text: "{{premise}}\n\nBased on that paragraph can we conclude that this sentence is true?\n{{hypothesis}}\n\nOPTIONS:\n- Yes\n- It's impossible to say\n- No"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-2":
-    doc_to_text: "{{premise}}\n\nCan we draw the following conclusion?\n{{hypothesis}}\n\nOPTIONS:\n- Yes\n- It's impossible to say\n- No"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-3":
-    doc_to_text: "{{premise}}\nDoes this next sentence follow, given the preceding text?\n{{hypothesis}}\n\nOPTIONS:\n- Yes\n- It's impossible to say\n- No"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-4":
-    doc_to_text: "{{premise}}\nCan we infer the following?\n{{hypothesis}}\n\nOPTIONS:\n- Yes\n- It's impossible to say\n- No\nThe answer is:"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-5":
-    doc_to_text: "Read the following paragraph and determine if the hypothesis is true:\n\n{{premise}}\n\nOPTIONS:\n- Yes\n- It's impossible to say\n- No\nHypothesis: {{hypothesis}}\n\n\n"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-6":
-    doc_to_text: "Read the text and determine if the sentence is true (see options at the end):\n\n{{premise}}\n\nSentence: {{hypothesis}}\nOPTIONS:\n- Yes\n- It's impossible to say\n- No"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-7":
-    doc_to_text: "Can we draw the following hypothesis from the context (see options)? \n\nContext:\n\n{{premise}}\n\nHypothesis: {{hypothesis}}\nOPTIONS:\n- Yes\n- It's impossible to say\n- No"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"
-  "template-8":
-    doc_to_text: "Choose from options: Determine if the sentence is true based on the text below:\n{{hypothesis}}\n\n{{premise}}\nOPTIONS:\n- Yes\n- It's impossible to say\n- No"
-    doc_to_target: "{{[\"Yes\", \"It's impossible to say\", \"No\"][label]}}"

lm_eval/tasks/benchmarks/flan/prompt_templates/flan_arc.yaml

-# Flan Prompt Templates
-prompts:
-  "template-0":
-    doc_to_text: "{{question}}\n\nOPTIONS:\n- {{choices.text|join('\n- ')}}"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"
-  "template-1":
-    doc_to_text: "Question: {{question}}\nOPTIONS:\n- {{choices.text|join('\n- ')}}\nAnswer:"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"
-  "template-2":
-    doc_to_text: "Question: {{question}}\n\nWhat is the correct answer to the question from the following choices?\nOPTIONS:\n- {{choices.text|join('\n- ')}}"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"
-  "template-3":
-    doc_to_text: "Q: {{question}}\nWhat is the correct answer to this question?\nOPTIONS:\n- {{choices.text|join('\n- ')}}...A:"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"
-  "template-4":
-    doc_to_text: "Choose your answer?\n\n{{question}}\n\nOPTIONS:\n- {{choices.text|join('\n- ')}}"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"
-  "template-5":
-    doc_to_text: "Answer the question\n\n{{question}}\nOPTIONS:\n- {{choices.text|join('\n- ')}}"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"
-  "template-6":
-    doc_to_text: "{{question}}\n\nPick the answer from these options\n\nOPTIONS:\n- {{choices.text|join('\n- ')}}"
-    doc_to_target: "{{choices.text[choices.label.index(answerKey)]}}"

lm_eval/tasks/benchmarks/flan/prompt_templates/flan_boolq.yaml

-# Flan Prompt Templates
-prompts:
-  "template-0":
-    doc_to_text: "{{passage}}\n\nCan we conclude that {{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-1":
-    doc_to_text: "{{passage}}\n\nIs it true that {{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-2":
-    doc_to_text: "{{passage}}\n\n{{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-3":
-    doc_to_text: "Text: {{passage}}\n\nQuestion: {{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-4":
-    doc_to_text: "{{passage}}\n\nWhat's the best answer to this question: {{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-5":
-    doc_to_text: "{{passage}}\nBased on the above text what's the best answer to this question: {{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-6":
-    doc_to_text: "{{passage}}\nAnswer this question making sure that the answer is supposed by the text: {{question}}?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-7":
-    doc_to_text: "{{passage}}\n\nIs the following statement correct based on the text\n\n{{question}}\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-8":
-    # doc_to_text: "{{title}}\n\n{{passage}}\n\nIs this statement correct \"{{question}}\"?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_text: "{{passage}}\n\nIs this statement correct \"{{question}}\"?\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"
-  "template-9":
-    doc_to_text: "Is it true that {{question}} based on the following text?\n\n{{passage}}\n\nOPTIONS:\n- no\n- yes"
-    doc_to_target: "{{['no', 'yes'][label]}}"

lm_eval/tasks/benchmarks/flan/prompt_templates/flan_rte.yaml

-# Flan Prompt Templates
-prompts:
-  "template-0":
-    doc_to_text: "{{premise}}\n\nQuestion with options: Based on the paragraph above can we conclude that \"{{hypothesis}}\"?\n\nOPTIONS:\n- yes\n- no"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-1":
-    doc_to_text: "{{premise}}\n\nBased on that paragraph can we conclude that the sentence below is true?\n{{hypothesis}}\n\nOPTIONS:\n- yes\n- no"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-2":
-    doc_to_text: "{{premise}}\n\nQ with options: Can we draw the following conclusion?\n{{hypothesis}}\n\nOPTIONS:\n- yes\n- no"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-3":
-    doc_to_text: "{{premise}}\nDoes this next sentence follow, given the preceding text?\n{{hypothesis}}\n\nOPTIONS:\n- yes\n- no"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-4":
-    doc_to_text: "{{premise}}\nOPTIONS:\n- yes\n- no\nQuestion: Can we infer the following?\n{{hypothesis}}"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-5":
-    doc_to_text: "Read the following paragraph and determine if the hypothesis is true. Select from options at the end:\n\n{{premise}}\n\nHypothesis: {{hypothesis}}\nOPTIONS:\n- yes\n- no\nThe answer is"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-6":
-    doc_to_text: "Read the text and determine if the sentence is true:\n\n{{premise}}\n\nSentence: {{hypothesis}}\nOPTIONS:\n- yes\n- no\nA:"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-7":
-    doc_to_text: "Question with options: can we draw the following hypothesis from the context? \n\nContext:\n\n{{premise}}\n\nHypothesis: {{hypothesis}}\nOPTIONS:\n- yes\n- no\nA:"
-    doc_to_target: "{{['yes', 'no'][label]}}"
-  "template-8":
-    doc_to_text: "Determine if the sentence is true based on the text below. Choose from options.\n{{hypothesis}}\n\n{{premise}}\nOPTIONS:\n- yes\n- no"
-    doc_to_target: "{{['yes', 'no'][label]}}"

main.py

@@ -10,7 +10,7 @@ from pathlib import Path
 from lm_eval import evaluator, utils
 from lm_eval.api.registry import ALL_TASKS
 from lm_eval.logger import eval_logger, SPACING
-from lm_eval.tasks import include_task_folder
+from lm_eval.tasks import include_path
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
@@ -111,7 +111,7 @@ def main() -> None:
 
     if args.include_path is not None:
         eval_logger.info(f"Including path: {args.include_path}")
-        include_task_folder(args.include_path)
+        include_path(args.include_path)
 
     if args.tasks is None:
         task_names = ALL_TASKS