# Language modeling
language_modeling_example = {"text": "The sky is blue."}
# Preference
preference_example = {"prompt": "The sky is", "chosen": " blue.", "rejected": " green."}
# Unpaired preference
unpaired_preference_example = {"prompt": "The sky is", "completion": " blue.", "label": True}

messages = [
    {"role": "user", "content": "Hello, how are you?"},
    {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
    {"role": "user", "content": "I'd like to show off how chat templating works!"},
]

# Prompt-completion
prompt_completion_example = {"prompt": [{"role": "user", "content": "What color is the sky?"}],
                             "completion": [{"role": "assistant", "content": "It is blue."}]}
# Preference
preference_example = {
    "prompt": [{"role": "user", "content": "What color is the sky?"}],
    "chosen": [{"role": "assistant", "content": "It is blue."}],
    "rejected": [{"role": "assistant", "content": "It is green."}],
}

messages = [
    {"role": "user", "content": "Turn on the living room lights."},
    {"role": "assistant", "tool_calls": [
        {"type": "function", "function": {
            "name": "control_light",
            "arguments": {"room": "living room", "state": "on"}
        }}]
    },
    {"role": "tool", "name": "control_light", "content": "The lights in the living room are now on."},
    {"role": "assistant", "content": "Done!"}
]

import json
from transformers.utils import get_json_schema

def control_light(room: str, state: str) -> str:
    """
    Controls the lights in a room.

    Args:
        room: The name of the room.
        state: The desired state of the light ("on" or "off").

    Returns:
        str: A message indicating the new state of the lights.
    """
    return f"The lights in {room} are now {state}."

# Generate JSON schema
json_schema = get_json_schema(control_light)

{"type": "function", "function": {"name": "control_light", "description": "Controls the lights in a room.", "parameters": {"type": "object", "properties": {"room": {"type": "string", "description": "The name of the room."}, "state": {"type": "string", "description": "The desired state of the light (\"on\" or \"off\")."}}, "required": ["room", "state"]}, "return": {"type": "string", "description": "str: A message indicating the new state of the lights."}}}

{"messages": messages, "tools": [json_schema]}

from datasets import Dataset

data = [
    {"messages": messages1, "tools": [json_schema1]},
    {"messages": messages2, "tools": [json_schema2]},
]
# auto-apply the Json() type
dataset = Dataset.from_list(data, on_mixed_types="use_json")

# or specify the features manually
from datasets import Features, Json, List, Value

features = Features(
    {
        "messages": List({"role": Value("string"), "content": Value("string"), "tool_calls": List(Json())}),
        "tools": List(Json()),
    }
)
dataset = Dataset.from_list(data, features=features)

dataset = Dataset.from_list(
    [{"messages": messages1, "tools": json.dumps([json_schema1])},
     {"messages": messages2, "tools": json.dumps([json_schema2])}]
)

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-20b")

messages = [
    {"role": "developer", "content": "Use a friendly tone."},
    {"role": "user", "content": "What is the meaning of life?"},
    {"role": "assistant", "thinking": "Deep reflection...", "content": "The final answer is..."},
]

print(
    tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        reasoning_effort="low",
        model_identity="You are HuggingGPT, a large language model trained by Hugging Face.",
    )
)

<|start|>system<|message|>You are HuggingGPT, a large language model trained by Hugging Face.
Knowledge cutoff: 2024-06
Current date: 2025-08-03

Reasoning: low

# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions

Use a friendly tone.<|end|><|start|>user<|message|>What is the meaning of life?<|end|><|start|>assistant<|channel|>analysis<|message|>Deep reflection...<|end|><|start|>assistant<|channel|>final<|message|>The final answer is...<|return|>

# Standard format
language_modeling_example = {"text": "The sky is blue."}
# Conversational format
language_modeling_example = {"messages": [
    {"role": "user", "content": "What color is the sky?"},
    {"role": "assistant", "content": "It is blue."}
]}

# Standard format
prompt_only_example = {"prompt": "The sky is"}
# Conversational format
prompt_only_example = {"prompt": [{"role": "user", "content": "What color is the sky?"}]}

# Standard format
prompt_completion_example = {"prompt": "The sky is", "completion": " blue."}
# Conversational format
prompt_completion_example = {"prompt": [{"role": "user", "content": "What color is the sky?"}],
                             "completion": [{"role": "assistant", "content": "It is blue."}]}

# Standard format
## Explicit prompt (recommended)
preference_example = {"prompt": "The sky is", "chosen": " blue.", "rejected": " green."}
# Implicit prompt
preference_example = {"chosen": "The sky is blue.", "rejected": "The sky is green."}

# Conversational format
## Explicit prompt (recommended)
preference_example = {"prompt": [{"role": "user", "content": "What color is the sky?"}],
                      "chosen": [{"role": "assistant", "content": "It is blue."}],
                      "rejected": [{"role": "assistant", "content": "It is green."}]}
## Implicit prompt
preference_example = {"chosen": [{"role": "user", "content": "What color is the sky?"},
                                 {"role": "assistant", "content": "It is blue."}],
                      "rejected": [{"role": "user", "content": "What color is the sky?"},
                                   {"role": "assistant", "content": "It is green."}]}

# Standard format
unpaired_preference_example = {"prompt": "The sky is", "completion": " blue.", "label": True}
# Conversational format
unpaired_preference_example = {"prompt": [{"role": "user", "content": "What color is the sky?"}],
                               "completion": [{"role": "assistant", "content": "It is blue."}],
                               "label": True}

python examples/datasets/ultrafeedback.py --push_to_hub --repo_id trl-lib/ultrafeedback-gpt-3.5-turbo-helpfulness

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is"],
    "completion": [" blue.", " in the sky."],
})

def concat_prompt_completion(example):
    return {"text": example["prompt"] + example["completion"]}

dataset = dataset.map(concat_prompt_completion, remove_columns=["prompt", "completion"])

>>> dataset[0]
{'text': 'The sky is blue.'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is"],
    "completion": [" blue.", " in the sky."],
})

dataset = dataset.remove_columns("completion")

>>> dataset[0]
{'prompt': 'The sky is'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "chosen": ["The sky is blue.", "The sun is in the sky."],
    "rejected": ["The sky is green.", "The sun is in the sea."],
})

dataset = dataset.rename_column("chosen", "text").remove_columns("rejected")

>>> dataset[0]
{'text': 'The sky is blue.'}

from datasets import Dataset
from trl import extract_prompt

dataset = Dataset.from_dict({
    "chosen": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is blue."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sky."}],
    ],
    "rejected": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is green."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sea."}],
    ],
})
dataset = dataset.map(extract_prompt).remove_columns("rejected").rename_column("chosen", "completion")

>>> dataset[0]
{'prompt': [{'role': 'user', 'content': 'What color is the sky?'}], 'completion': [{'role': 'assistant', 'content': 'It is blue.'}]}

from datasets import Dataset
from trl import extract_prompt

dataset = Dataset.from_dict({
    "chosen": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is blue."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sky."}],
    ],
    "rejected": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is green."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sea."}],
    ],
})
dataset = dataset.map(extract_prompt).remove_columns(["chosen", "rejected"])

>>> dataset[0]
{'prompt': [{'role': 'user', 'content': 'What color is the sky?'}]}

from datasets import Dataset
from trl import extract_prompt

dataset = Dataset.from_dict({
    "chosen": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is blue."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sky."}],
    ],
    "rejected": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is green."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sea."}],
    ],
})

dataset = dataset.map(extract_prompt)

>>> dataset[0]
{'prompt': [{'role': 'user', 'content': 'What color is the sky?'}],
 'chosen': [{'role': 'assistant', 'content': 'It is blue.'}],
 'rejected': [{'role': 'assistant', 'content': 'It is green.'}]}

from datasets import Dataset
from trl import extract_prompt, unpair_preference_dataset

dataset = Dataset.from_dict({
    "chosen": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is blue."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sky."}],
    ],
    "rejected": [
        [{"role": "user", "content": "What color is the sky?"}, {"role": "assistant", "content": "It is green."}],
        [{"role": "user", "content": "Where is the sun?"}, {"role": "assistant", "content": "In the sea."}],
    ],
})

dataset = dataset.map(extract_prompt)
dataset = unpair_preference_dataset(dataset)

>>> dataset[0]
{'prompt': [{'role': 'user', 'content': 'What color is the sky?'}],
 'completion': [{'role': 'assistant', 'content': 'It is blue.'}],
 'label': True}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is"],
    "chosen": [" blue.", " in the sky."],
    "rejected": [" green.", " in the sea."],
})

def concat_prompt_chosen(example):
    return {"text": example["prompt"] + example["chosen"]}

dataset = dataset.map(concat_prompt_chosen, remove_columns=["prompt", "chosen", "rejected"])

>>> dataset[0]
{'text': 'The sky is blue.'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is"],
    "chosen": [" blue.", " in the sky."],
    "rejected": [" green.", " in the sea."],
})

dataset = dataset.remove_columns("rejected").rename_column("chosen", "completion")

>>> dataset[0]
{'prompt': 'The sky is', 'completion': ' blue.'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is"],
    "chosen": [" blue.", " in the sky."],
    "rejected": [" green.", " in the sea."],
})

dataset = dataset.remove_columns(["chosen", "rejected"])

>>> dataset[0]
{'prompt': 'The sky is'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": [
        [{"role": "user", "content": "What color is the sky?"}],
        [{"role": "user", "content": "Where is the sun?"}],
    ],
    "chosen": [
        [{"role": "assistant", "content": "It is blue."}],
        [{"role": "assistant", "content": "In the sky."}],
    ],
    "rejected": [
        [{"role": "assistant", "content": "It is green."}],
        [{"role": "assistant", "content": "In the sea."}],
    ],
})

def concat_prompt_to_completions(example):
    return {"chosen": example["prompt"] + example["chosen"], "rejected": example["prompt"] + example["rejected"]}

dataset = dataset.map(concat_prompt_to_completions, remove_columns="prompt")

>>> dataset[0]
{'chosen': [{'role': 'user', 'content': 'What color is the sky?'}, {'role': 'assistant', 'content': 'It is blue.'}],
 'rejected': [{'role': 'user', 'content': 'What color is the sky?'}, {'role': 'assistant', 'content': 'It is green.'}]}

from datasets import Dataset
from trl import unpair_preference_dataset

dataset = Dataset.from_dict({
    "prompt": [
        [{"role": "user", "content": "What color is the sky?"}],
        [{"role": "user", "content": "Where is the sun?"}],
    ],
    "chosen": [
        [{"role": "assistant", "content": "It is blue."}],
        [{"role": "assistant", "content": "In the sky."}],
    ],
    "rejected": [
        [{"role": "assistant", "content": "It is green."}],
        [{"role": "assistant", "content": "In the sea."}],
    ],
})

dataset = unpair_preference_dataset(dataset)

>>> dataset[0]
{'prompt': [{'role': 'user', 'content': 'What color is the sky?'}],
 'completion': [{'role': 'assistant', 'content': 'It is blue.'}],
 'label': True}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is", "The sky is", "The sun is"],
    "completion": [" blue.", " in the sky.", " green.", " in the sea."],
    "label": [True, True, False, False],
})

def concatenate_prompt_completion(example):
    return {"text": example["prompt"] + example["completion"]}

dataset = dataset.filter(lambda x: x["label"]).map(concatenate_prompt_completion).remove_columns(["prompt", "completion", "label"])

>>> dataset[0]
{'text': 'The sky is blue.'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is", "The sky is", "The sun is"],
    "completion": [" blue.", " in the sky.", " green.", " in the sea."],
    "label": [True, True, False, False],
})

dataset = dataset.filter(lambda x: x["label"]).remove_columns(["label"])

>>> dataset[0]
{'prompt': 'The sky is', 'completion': ' blue.'}

from datasets import Dataset

dataset = Dataset.from_dict({
    "prompt": ["The sky is", "The sun is", "The sky is", "The sun is"],
    "completion": [" blue.", " in the sky.", " green.", " in the sea."],
    "label": [True, True, False, False],
})

dataset = dataset.remove_columns(["completion", "label"])

>>> dataset[0]
{'prompt': 'The sky is'}

# Textual dataset:
"content": "What color is the sky?"

# Vision dataset:
"content": [
    {"type": "image"},
    {"type": "text", "text": "What color is the sky in the image?"}
]