added deepseekv2

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/temporal_sequences.yaml

+"dataset_name": "temporal_sequences"
+"description": "Task description: Answer questions about which times certain events could have occurred.\n\n"
+"doc_to_text": "Q: Today, Emily went to the museum. Between what times could they have gone?\nWe know that:\nEmily woke up at 1pm.\nElizabeth saw Emily reading at the library from 2pm to 4pm.\nJessica saw Emily watching a movie at the theater from 4pm to 5pm.\nLeslie saw Emily waiting at the airport from 5pm to 6pm.\nWilliam saw Emily buying clothes at the mall from 6pm to 7pm.\nThe museum was closed after 7pm.\nBetween what times could Emily have gone to the museum?\nOptions:\n(A) 1pm to 2pm\n(B) 6pm to 7pm\n(C) 5pm to 6pm\n(D) 2pm to 4pm\nA: (A)\n\nQ: Today, Elizabeth went to the amusement park. Between what times could they have gone?\nWe know that:\nElizabeth woke up at 7am.\nDavid saw Elizabeth fixing their computer at the electronic store from 1pm to 2pm.\nSarah saw Elizabeth playing tennis at the tennis court from 2pm to 3pm.\nSusan saw Elizabeth walking towards the Statue of Liberty from 3pm to 6pm.\nAndrew saw Elizabeth taking photos near the Eiffel Tower from 6pm to 9pm.\nEmily saw Elizabeth getting a coffee at the cafe from 9pm to 10pm.\nThe amusement park was closed after 10pm.\nBetween what times could Elizabeth have gone to the amusement park?\nOptions:\n(A) 7am to 1pm\n(B) 9pm to 10pm\n(C) 1pm to 2pm\n(D) 3pm to 6pm\nA: (A)\n\nQ: Today, Tiffany went to the beach. Between what times could they have gone?\nWe know that:\nTiffany woke up at 5am.\nBetty saw Tiffany getting a coffee at the cafe from 5am to 6am.\nJessica saw Tiffany working at the office from 6am to 9am.\nJohn saw Tiffany stretching at a yoga studio from 9am to 12pm.\nSean saw Tiffany sitting on a rooftop from 12pm to 2pm.\nSarah saw Tiffany playing tennis at the tennis court from 2pm to 3pm.\nThe beach was closed after 4pm.\nBetween what times could Tiffany have gone to the beach?\nOptions:\n(A) 9am to 12pm\n(B) 12pm to 2pm\n(C) 5am to 6am\n(D) 3pm to 4pm\nA: (D)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_temporal_sequences"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_five_objects.yaml

+"dataset_name": "tracking_shuffled_objects_five_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_tracking_shuffled_objects_five_objects"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_seven_objects.yaml

+"dataset_name": "tracking_shuffled_objects_seven_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_tracking_shuffled_objects_seven_objects"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_three_objects.yaml

+"dataset_name": "tracking_shuffled_objects_three_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_tracking_shuffled_objects_three_objects"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/web_of_lies.yaml

+"dataset_name": "web_of_lies"
+"description": "Evaluate a random boolean function expressed as a word problem.\n\n"
+"doc_to_text": "Q: Question: Fidel tells the truth. Jerry says Fidel tells the truth. Vina says Jerry tells the truth. Millicent says Vina lies. Raymond says Millicent lies. Does Raymond tell the truth?\nA: Yes\n\nQ: Question: Kristian lies. Millie says Kristian lies. Maybelle says Millie tells the truth. Fidel says Maybelle lies. Leda says Fidel lies. Does Leda tell the truth?\nA: Yes\n\nQ: Question: Kristian tells the truth. Michaela says Kristian lies. Raymond says Michaela tells the truth. Osvaldo says Raymond tells the truth. Jamey says Osvaldo tells the truth. Does Jamey tell the truth?\nA: No\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_web_of_lies"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/word_sorting.yaml

+"dataset_name": "word_sorting"
+"description": "Sort a list of words.\n\n"
+"doc_to_text": "Q: Sort the following words alphabetically: List: oven costume counterpart\nA: costume counterpart oven\n\nQ: Sort the following words alphabetically: List: hypochlorite ponderosa phone credulity\nA: credulity hypochlorite phone ponderosa\n\nQ: Sort the following words alphabetically: List: newt arson parthia seismography mugho aspect census\nA: arson aspect census mugho newt parthia seismography\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_word_sorting"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/_zeroshot_template_yaml

+group: bbh_zeroshot
+dataset_path: lukaemon/bbh
+output_type: generate_until
+test_split: test
+doc_to_target: "{{target}}"
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    # ignore_punctuation: true
+    regexes_to_ignore:
+      - "\\.$"
+      - ","
+      - "\n"
+      - "\\\\"
+      - '"'
+generation_kwargs:
+  until:
+    - "</s>"
+    - "Q:"
+    - "<|im_end|>"
+  do_sample: false
+  temperature: 0.0
+num_fewshot: 0
+metadata:
+  version: 2.0

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/boolean_expressions.yaml

+"dataset_name": "boolean_expressions"
+"description": "Evaluate the result of a random Boolean expression.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_boolean_expressions"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: "regex"
+        group_select: 0
+        regex_pattern: "\\b(True|False)\\b"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/causal_judgement.yaml

+"dataset_name": "causal_judgement"
+"description": "Answer questions about causal attribution.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_causal_judgement"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: "regex"
+        group_select: 0
+        regex_pattern: "\\b(Yes|No|yes|no)\\b"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/date_understanding.yaml

+"dataset_name": "date_understanding"
+"description": "Infer the date from context.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_date_understanding"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/disambiguation_qa.yaml

+"dataset_name": "disambiguation_qa"
+"description": "Clarify the meaning of sentences with ambiguous pronouns.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_disambiguation_qa"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/dyck_languages.yaml

+"dataset_name": "dyck_languages"
+"description": "Correctly close a Dyck-n word.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_dyck_languages"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: "regex"
+        group_select: 0
+        regex_pattern: "(?<= )([\" \\[\\(<{}>\\)\\]]+)|([\" \\[\\(<{}>\\)\\]]+)"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/formal_fallacies.yaml

+"dataset_name": "formal_fallacies"
+"description": "Distinguish deductively valid arguments from formal fallacies.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_formal_fallacies"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: "regex"
+        group_select: 0
+        regex_pattern: "\\b(valid|invalid)\\b"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/geometric_shapes.yaml

+"dataset_name": "geometric_shapes"
+"description": "Name geometric shapes from their SVG paths.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_geometric_shapes"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/hyperbaton.yaml

+"dataset_name": "hyperbaton"
+"description": "Order adjectives correctly in English sentences.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_hyperbaton"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/logical_deduction_five_objects.yaml

+"dataset_name": "logical_deduction_five_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_logical_deduction_five_objects"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/logical_deduction_seven_objects.yaml

+"dataset_name": "logical_deduction_seven_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_logical_deduction_seven_objects"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/logical_deduction_three_objects.yaml

+"dataset_name": "logical_deduction_three_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_logical_deduction_three_objects"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/movie_recommendation.yaml

+"dataset_name": "movie_recommendation"
+"description": "Recommend movies similar to the given list of movies.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_movie_recommendation"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: 0
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/zeroshot/multistep_arithmetic_two.yaml

+"dataset_name": "multistep_arithmetic_two"
+"description": "Solve multi-step arithmetic problems.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_multistep_arithmetic_two"
+
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.NumberParseRegexFilter
+        group_select: 0
+        regex_pattern: "([-0-9]+)"
+      - function: "take_first"