oumi.datasets.grpo#

GRPO datasets module.

class oumi.datasets.grpo.BerryBenchGrpoDataset(*, dataset_name: str | None = None, dataset_path: str | None = None, split: str | None = None, **kwargs)[source]#

Bases: BaseExperimentalGrpoDataset

Dataset class for the oumi-ai/berrybench-v0.1.1 dataset.

A sample from the dataset: {

“messages”: [

{

“content”: “Return a JSON object showing the frequency of each character in the word ‘黒い’. Only include characters that appear in the word.”, “role”: “user”,

}

], “metadata”: {

“character_count”: 2, “difficulty”: 3, “expected_response”: ‘{”\u9ed2”: 1, “\u3044”: 1}’, “language”: “japanese”, “word”: “黒い”,

},

}

dataset_name: str#

default_dataset: str | None = 'oumi-ai/berrybench-v0.1.1'#

transform(sample: Series) → dict[source]#

Transform the sample into Python dict.

transform_conversation(sample: Series) → Conversation[source]#

Converts the input sample to a Conversation.

Parameters:

sample (dict) – The input example.

Returns:

The resulting conversation.

Return type:

Conversation

trust_remote_code: bool#

class oumi.datasets.grpo.CountdownGrpoDataset(*, dataset_name: str | None = None, dataset_path: str | None = None, split: str | None = None, **kwargs)[source]#

Bases: BaseExperimentalGrpoDataset

Dataset class for the d1shs0ap/countdown dataset.

A sample from the dataset: {“target”: 87, “nums”: [79, 8]}

dataset_name: str#

default_dataset: str | None = 'd1shs0ap/countdown'#

transform(sample: Series) → dict[source]#

Validate and transform the sample into Python dict.

transform_conversation(sample: Series) → Conversation[source]#

Validate and transform the sample into Python dict.

trust_remote_code: bool#

class oumi.datasets.grpo.LetterCountGrpoDataset(*, dataset_name: str | None = None, dataset_path: str | None = None, split: str | None = None, **kwargs)[source]#

Bases: BaseExperimentalGrpoDataset

Dataset class for the oumi-ai/oumi-letter-count dataset.

A sample from the dataset: {

“conversation_id”: “oumi_letter_count_0”, “messages”: [

{

“content”: “Can you let me know how many ‘r’s are in ‘pandered’?”, “role”: “user”,

}

], “metadata”: {

“letter”: “r”, “letter_count_integer”: 1, “letter_count_string”: “one”, “unformatted_prompt”: “Can you let me know how many {letter}s are in {word}?”, “word”: “pandered”,

},

}

dataset_name: str#

default_dataset: str | None = 'oumi-ai/oumi-letter-count'#

transform(sample: Series) → dict[source]#

Validate and transform the sample into Python dict.

transform_conversation(sample: Series) → Conversation[source]#

Converts the input sample to a Conversation.

Parameters:

sample (dict) – The input example.

Returns:

The resulting conversation.

Return type:

Conversation

trust_remote_code: bool#

class oumi.datasets.grpo.TldrGrpoDataset(*, dataset_name: str | None = None, dataset_path: str | None = None, split: str | None = None, **kwargs)[source]#

Bases: BaseExperimentalGrpoDataset

Dataset class for the trl-lib/tldr dataset.

dataset_name: str#

default_dataset: str | None = 'trl-lib/tldr'#

trust_remote_code: bool#