Hugging Face

This section contains the reference for Hugging Face integrations:

Inference Endpoints

InferenceEndpointsLLM

Bases: AsyncLLM

InferenceEndpoints LLM implementation running the async API client via either the huggingface_hub.AsyncInferenceClient or via openai.AsyncOpenAI.

Attributes:

Name	Type	Description
model_id	Optional[str]	the model ID to use for the LLM as available in the Hugging Face Hub, which will be used to resolve the base URL for the serverless Inference Endpoints API requests. Defaults to None.
endpoint_name	Optional[RuntimeParameter[str]]	the name of the Inference Endpoint to use for the LLM. Defaults to None.
endpoint_namespace	Optional[RuntimeParameter[str]]	the namespace of the Inference Endpoint to use for the LLM. Defaults to None.
base_url	Optional[RuntimeParameter[str]]	the base URL to use for the Inference Endpoints API requests.
api_key	Optional[RuntimeParameter[SecretStr]]	the API key to authenticate the requests to the Inference Endpoints API.
tokenizer_id	Optional[str]	the tokenizer ID to use for the LLM as available in the Hugging Face Hub. Defaults to None, but defining one is recommended to properly format the prompt.
model_display_name	Optional[str]	the model display name to use for the LLM. Defaults to None.
use_openai_client	bool	whether to use the OpenAI client instead of the Hugging Face client.

Examples:

from distilabel.llms.huggingface import InferenceEndpointsLLM

# Free serverless Inference API
llm = InferenceEndpointsLLM(
    model_id="mistralai/Mistral-7B-Instruct-v0.2",
)

# Dedicated Inference Endpoints
llm = InferenceEndpointsLLM(
    endpoint_name="<ENDPOINT_NAME>",
    api_key="<HF_API_KEY>",
    endpoint_namespace="<USER|ORG>",
)

# Dedicated Inference Endpoints or TGI
llm = InferenceEndpointsLLM(
    api_key="<HF_API_KEY>",
    base_url="<BASE_URL>",
)

llm.load()

# Synchrounous request
output = llm.generate(inputs=[[{"role": "user", "content": "Hello world!"}]])

# Asynchronous request
output = await llm.agenerate(input=[{"role": "user", "content": "Hello world!"}])

Source code in src/distilabel/llms/huggingface/inference_endpoints.py

class InferenceEndpointsLLM(AsyncLLM):
    """InferenceEndpoints LLM implementation running the async API client via either
    the `huggingface_hub.AsyncInferenceClient` or via `openai.AsyncOpenAI`.

    Attributes:
        model_id: the model ID to use for the LLM as available in the Hugging Face Hub, which
            will be used to resolve the base URL for the serverless Inference Endpoints API requests.
            Defaults to `None`.
        endpoint_name: the name of the Inference Endpoint to use for the LLM. Defaults to `None`.
        endpoint_namespace: the namespace of the Inference Endpoint to use for the LLM. Defaults to `None`.
        base_url: the base URL to use for the Inference Endpoints API requests.
        api_key: the API key to authenticate the requests to the Inference Endpoints API.
        tokenizer_id: the tokenizer ID to use for the LLM as available in the Hugging Face Hub.
            Defaults to `None`, but defining one is recommended to properly format the prompt.
        model_display_name: the model display name to use for the LLM. Defaults to `None`.
        use_openai_client: whether to use the OpenAI client instead of the Hugging Face client.

    Examples:
        ```python
        from distilabel.llms.huggingface import InferenceEndpointsLLM

        # Free serverless Inference API
        llm = InferenceEndpointsLLM(
            model_id="mistralai/Mistral-7B-Instruct-v0.2",
        )

        # Dedicated Inference Endpoints
        llm = InferenceEndpointsLLM(
            endpoint_name="<ENDPOINT_NAME>",
            api_key="<HF_API_KEY>",
            endpoint_namespace="<USER|ORG>",
        )

        # Dedicated Inference Endpoints or TGI
        llm = InferenceEndpointsLLM(
            api_key="<HF_API_KEY>",
            base_url="<BASE_URL>",
        )

        llm.load()

        # Synchrounous request
        output = llm.generate(inputs=[[{"role": "user", "content": "Hello world!"}]])

        # Asynchronous request
        output = await llm.agenerate(input=[{"role": "user", "content": "Hello world!"}])
        ```
    """

    model_id: Optional[str] = None

    endpoint_name: Optional[RuntimeParameter[str]] = Field(
        default=None,
        description="The name of the Inference Endpoint to use for the LLM.",
    )
    endpoint_namespace: Optional[RuntimeParameter[str]] = Field(
        default=None,
        description="The namespace of the Inference Endpoint to use for the LLM.",
    )
    base_url: Optional[RuntimeParameter[str]] = Field(
        default=None,
        description="The base URL to use for the Inference Endpoints API requests.",
    )
    api_key: Optional[RuntimeParameter[SecretStr]] = Field(
        default=os.getenv(_INFERENCE_ENDPOINTS_API_KEY_ENV_VAR_NAME),
        description="The API key to authenticate the requests to the Inference Endpoints API.",
    )

    tokenizer_id: Optional[str] = None
    model_display_name: Optional[str] = None
    use_openai_client: bool = False

    _model_name: Optional[str] = PrivateAttr(default=None)
    _tokenizer: Optional["PreTrainedTokenizer"] = PrivateAttr(default=None)
    _api_key_env_var: str = PrivateAttr(_INFERENCE_ENDPOINTS_API_KEY_ENV_VAR_NAME)
    _aclient: Optional[Union["AsyncInferenceClient", "AsyncOpenAI"]] = PrivateAttr(...)

    @model_validator(mode="after")  # type: ignore
    def only_one_of_model_id_endpoint_name_or_base_url_provided(
        self,
    ) -> "InferenceEndpointsLLM":
        """Validates that only one of `model_id` or `endpoint_name` is provided; and if `base_url` is also
        provided, a warning will be shown informing the user that the provided `base_url` will be ignored in
        favour of the dynamically calculated one.."""

        if self.base_url and (self.model_id or self.endpoint_name):
            self._logger.warning(  # type: ignore
                f"Since the `base_url={self.base_url}` is available and either one of `model_id` or `endpoint_name`"
                " is also provided, the `base_url` will either be ignored or overwritten with the one generated"
                " from either of those args, for serverless or dedicated inference endpoints, respectively."
            )

        if self.base_url and not (self.model_id or self.endpoint_name):
            return self

        if self.model_id and not self.endpoint_name:
            return self

        if self.endpoint_name and not self.model_id:
            return self

        raise ValidationError(
            "Only one of `model_id` or `endpoint_name` must be provided. If `base_url` is provided too,"
            " it will be overwritten instead. Found `model_id`={self.model_id}, `endpoint_name`={self.endpoint_name},"
            f" and `base_url`={self.base_url}."
        )

    def load(self) -> None:  # noqa: C901
        """Loads the either the `AsyncInferenceClient` or the `AsyncOpenAI` client to benefit
        from async requests, running the Hugging Face Inference Endpoint underneath via the
        `/v1/chat/completions` endpoint, exposed for the models running on TGI using the
        `text-generation` task.

        Raises:
            ImportError: if the `openai` Python client is not installed.
            ImportError: if the `huggingface-hub` Python client is not installed.
            ValueError: if the model is not currently deployed or is not running the TGI framework.
            ImportError: if the `transformers` Python client is not installed.
        """
        super().load()

        try:
            from huggingface_hub import (
                AsyncInferenceClient,
                InferenceClient,
                get_inference_endpoint,
            )
        except ImportError as ie:
            raise ImportError(
                "Hugging Face Hub Python client is not installed. Please install it using"
                " `pip install huggingface-hub`."
            ) from ie

        if self.api_key is None:
            raise ValueError(
                f"To use `{self.__class__.__name__}` an API key must be provided via `api_key`"
                f" attribute or runtime parameter, or set the environment variable `{self._api_key_env_var}`."
            )

        if self.model_id is not None:
            client = InferenceClient()
            status = client.get_model_status(self.model_id)

            if (
                status.state not in {"Loadable", "Loaded"}
                and status.framework != "text-generation-inference"
            ):
                raise ValueError(
                    f"Model {self.model_id} is not currently deployed or is not running the TGI framework"
                )

            self.base_url = client._resolve_url(
                model=self.model_id, task="text-generation"
            )

        if self.endpoint_name is not None:
            client = get_inference_endpoint(
                name=self.endpoint_name,
                namespace=self.endpoint_namespace,
                token=self.api_key.get_secret_value(),
            )
            if client.status in ["paused", "scaledToZero"]:
                client.resume().wait(timeout=300)
            elif client.status in ["initializing"]:
                client.wait(timeout=300)

            self.base_url = client.url
            self._model_name = client.repository

        if self.use_openai_client:
            try:
                from openai import AsyncOpenAI
            except ImportError as ie:
                raise ImportError(
                    "OpenAI Python client is not installed. Please install it using"
                    " `pip install openai`."
                ) from ie

            self._aclient = AsyncOpenAI(
                base_url=self.base_url,
                api_key=self.api_key.get_secret_value(),
                max_retries=6,
            )
        else:
            self._aclient = AsyncInferenceClient(
                model=self.base_url,
                token=self.api_key.get_secret_value(),
            )

        if self.tokenizer_id:
            try:
                from transformers import AutoTokenizer
            except ImportError as ie:
                raise ImportError(
                    "Transformers Python client is not installed. Please install it using"
                    " `pip install transformers`."
                ) from ie

            self._tokenizer = AutoTokenizer.from_pretrained(self.tokenizer_id)

    @property
    @override
    def model_name(self) -> Union[str, None]:  # type: ignore
        """Returns the model name used for the LLM."""
        return (
            self.model_display_name
            or self._model_name
            or self.model_id
            or self.endpoint_name
            or self.base_url
        )

    async def _openai_agenerate(
        self,
        input: "ChatType",
        max_new_tokens: int = 128,
        frequency_penalty: float = 0.0,
        presence_penalty: float = 0.0,
        temperature: float = 1.0,
        top_p: Optional[float] = None,
        stop: Optional[Union[str, List[str]]] = None,
    ) -> GenerateOutput:
        """Generates completions for the given input using the OpenAI async client."""
        completion = await self._aclient.chat.completions.create(  # type: ignore
            messages=input,  # type: ignore
            model="tgi",
            max_tokens=max_new_tokens,
            n=1,
            frequency_penalty=frequency_penalty,
            presence_penalty=presence_penalty,
            temperature=temperature,
            top_p=top_p,
            stop=stop,
            timeout=50,
        )
        if completion.choices[0].message.content is None:
            self._logger.warning(  # type: ignore
                f"⚠️ Received no response using OpenAI client (model: '{self.model_name}')."
                f" Finish reason was: {completion.choices[0].finish_reason}"
            )
        return [completion.choices[0].message.content]

    # TODO: add `num_generations` parameter once either TGI or `AsyncInferenceClient` allows `n` parameter
    @validate_call
    async def agenerate(  # type: ignore
        self,
        input: ChatType,
        max_new_tokens: int = 128,
        frequency_penalty: float = 0.0,
        presence_penalty: float = 0.0,
        repetition_penalty: Optional[float] = None,
        temperature: float = 1.0,
        do_sample: bool = False,
        top_k: Optional[int] = None,
        top_p: Optional[float] = None,
        typical_p: Optional[float] = None,
        stop_sequences: Optional[Union[str, List[str]]] = None,
    ) -> "GenerateOutput":
        """Generates completions for the given input using the OpenAI async client.

        Args:
            input: a single input in chat format to generate responses for.
            max_new_tokens: the maximum number of new tokens that the model will generate.
                Defaults to `128`.
            frequency_penalty: the repetition penalty to use for the generation. Defaults
                to `0.0`. Only applies if `use_openai_client=True`.
            presence_penalty: the presence penalty to use for the generation. Defaults to
                `0.0`. Only applies if `use_openai_client=True`.
            repetition_penalty: the repetition penalty to use for the generation. Defaults
                to `None`. Only applies if `use_openai_client=False`.
            temperature: the temperature to use for the generation. Defaults to `1.0`.
            do_sample: whether to use sampling for the generation. Defaults to `False`.
                Only applies if `use_openai_client=False`.
            top_k: the top-k value to use for the generation. Defaults to `0.8`, since neither
                `0.0` nor `1.0` are valid values in TGI.
            top_p: the top-p value to use for the generation. Defaults to `1.0`.
            typical_p: the typical-p value to use for the generation. Defaults to `0.5`.
            stop_sequences: either a single string or a list of strings containing the sequences
                to stop the generation at. Defaults to `None`, but will be set to the
                `tokenizer.eos_token` if available.

        Returns:
            A list of lists of strings containing the generated responses for each input.
        """
        if stop_sequences is not None:
            if isinstance(stop_sequences, str):
                stop_sequences = [stop_sequences]
            if len(stop_sequences) > 4:
                warnings.warn(
                    "Only up to 4 stop sequences are allowed, so keeping the first 4 items only.",
                    UserWarning,
                    stacklevel=2,
                )
                stop_sequences = stop_sequences[:4]

        if self.use_openai_client:
            return await self._openai_agenerate(
                input=input,
                max_new_tokens=max_new_tokens,
                frequency_penalty=frequency_penalty,
                presence_penalty=presence_penalty,
                temperature=temperature,
                top_p=top_p,
                stop=stop_sequences,
            )

        if self._tokenizer is not None:
            prompt = self._tokenizer.apply_chat_template(  # type: ignore
                conversation=input,  # type: ignore
                tokenize=False,
                add_generation_prompt=True,
            )
        else:
            prompt = "\n".join([message["content"] for message in input])

        try:
            completion = await self._aclient.text_generation(  # type: ignore
                prompt=prompt,  # type: ignore
                max_new_tokens=max_new_tokens,
                do_sample=do_sample,
                typical_p=typical_p,
                repetition_penalty=repetition_penalty,
                temperature=temperature,
                top_p=top_p,
                top_k=top_k,
                # NOTE: here to ensure that the cache is not used and a different response is
                # generated every time
                seed=random.randint(0, 2147483647),
                stop_sequences=stop_sequences,
            )
            return [completion]
        except Exception as e:
            self._logger.warning(  # type: ignore
                f"⚠️ Received no response using Inference Client (model: '{self.model_name}')."
                f" Finish reason was: {e}"
            )
            return [None]

    # TODO: remove this function once `AsyncInferenceClient` allows `n` parameter
    @override
    def generate(
        self,
        inputs: List["ChatType"],
        num_generations: int = 1,
        **kwargs: Any,
    ) -> List["GenerateOutput"]:
        """Method to generate a list of responses asynchronously, returning the output
        synchronously awaiting for the response of each input sent to `agenerate`.
        """

        async def agenerate(
            inputs: List["ChatType"], **kwargs: Any
        ) -> "GenerateOutput":
            """Internal function to parallelize the asynchronous generation of responses."""
            tasks = [
                asyncio.create_task(self.agenerate(input=input, **kwargs))
                for input in inputs
                for _ in range(num_generations)
            ]
            return [outputs[0] for outputs in await asyncio.gather(*tasks)]

        outputs = self.event_loop.run_until_complete(agenerate(inputs, **kwargs))
        return list(grouper(outputs, n=num_generations, incomplete="ignore"))

model_name: Union[str, None] property

Returns the model name used for the LLM.

agenerate(input, max_new_tokens=128, frequency_penalty=0.0, presence_penalty=0.0, repetition_penalty=None, temperature=1.0, do_sample=False, top_k=None, top_p=None, typical_p=None, stop_sequences=None) async

Generates completions for the given input using the OpenAI async client.

Parameters:

Name	Type	Description	Default
input	ChatType	a single input in chat format to generate responses for.	required
max_new_tokens	int	the maximum number of new tokens that the model will generate. Defaults to 128.	128
frequency_penalty	float	the repetition penalty to use for the generation. Defaults to 0.0. Only applies if use_openai_client=True.	0.0
presence_penalty	float	the presence penalty to use for the generation. Defaults to 0.0. Only applies if use_openai_client=True.	0.0
repetition_penalty	Optional[float]	the repetition penalty to use for the generation. Defaults to None. Only applies if use_openai_client=False.	None
temperature	float	the temperature to use for the generation. Defaults to 1.0.	1.0
do_sample	bool	whether to use sampling for the generation. Defaults to False. Only applies if use_openai_client=False.	False
top_k	Optional[int]	the top-k value to use for the generation. Defaults to 0.8, since neither 0.0 nor 1.0 are valid values in TGI.	None
top_p	Optional[float]	the top-p value to use for the generation. Defaults to 1.0.	None
typical_p	Optional[float]	the typical-p value to use for the generation. Defaults to 0.5.	None
stop_sequences	Optional[Union[str, List[str]]]	either a single string or a list of strings containing the sequences to stop the generation at. Defaults to None, but will be set to the tokenizer.eos_token if available.	None

Returns:

Type	Description
GenerateOutput	A list of lists of strings containing the generated responses for each input.

Source code in src/distilabel/llms/huggingface/inference_endpoints.py

@validate_call
async def agenerate(  # type: ignore
    self,
    input: ChatType,
    max_new_tokens: int = 128,
    frequency_penalty: float = 0.0,
    presence_penalty: float = 0.0,
    repetition_penalty: Optional[float] = None,
    temperature: float = 1.0,
    do_sample: bool = False,
    top_k: Optional[int] = None,
    top_p: Optional[float] = None,
    typical_p: Optional[float] = None,
    stop_sequences: Optional[Union[str, List[str]]] = None,
) -> "GenerateOutput":
    """Generates completions for the given input using the OpenAI async client.

    Args:
        input: a single input in chat format to generate responses for.
        max_new_tokens: the maximum number of new tokens that the model will generate.
            Defaults to `128`.
        frequency_penalty: the repetition penalty to use for the generation. Defaults
            to `0.0`. Only applies if `use_openai_client=True`.
        presence_penalty: the presence penalty to use for the generation. Defaults to
            `0.0`. Only applies if `use_openai_client=True`.
        repetition_penalty: the repetition penalty to use for the generation. Defaults
            to `None`. Only applies if `use_openai_client=False`.
        temperature: the temperature to use for the generation. Defaults to `1.0`.
        do_sample: whether to use sampling for the generation. Defaults to `False`.
            Only applies if `use_openai_client=False`.
        top_k: the top-k value to use for the generation. Defaults to `0.8`, since neither
            `0.0` nor `1.0` are valid values in TGI.
        top_p: the top-p value to use for the generation. Defaults to `1.0`.
        typical_p: the typical-p value to use for the generation. Defaults to `0.5`.
        stop_sequences: either a single string or a list of strings containing the sequences
            to stop the generation at. Defaults to `None`, but will be set to the
            `tokenizer.eos_token` if available.

    Returns:
        A list of lists of strings containing the generated responses for each input.
    """
    if stop_sequences is not None:
        if isinstance(stop_sequences, str):
            stop_sequences = [stop_sequences]
        if len(stop_sequences) > 4:
            warnings.warn(
                "Only up to 4 stop sequences are allowed, so keeping the first 4 items only.",
                UserWarning,
                stacklevel=2,
            )
            stop_sequences = stop_sequences[:4]

    if self.use_openai_client:
        return await self._openai_agenerate(
            input=input,
            max_new_tokens=max_new_tokens,
            frequency_penalty=frequency_penalty,
            presence_penalty=presence_penalty,
            temperature=temperature,
            top_p=top_p,
            stop=stop_sequences,
        )

    if self._tokenizer is not None:
        prompt = self._tokenizer.apply_chat_template(  # type: ignore
            conversation=input,  # type: ignore
            tokenize=False,
            add_generation_prompt=True,
        )
    else:
        prompt = "\n".join([message["content"] for message in input])

    try:
        completion = await self._aclient.text_generation(  # type: ignore
            prompt=prompt,  # type: ignore
            max_new_tokens=max_new_tokens,
            do_sample=do_sample,
            typical_p=typical_p,
            repetition_penalty=repetition_penalty,
            temperature=temperature,
            top_p=top_p,
            top_k=top_k,
            # NOTE: here to ensure that the cache is not used and a different response is
            # generated every time
            seed=random.randint(0, 2147483647),
            stop_sequences=stop_sequences,
        )
        return [completion]
    except Exception as e:
        self._logger.warning(  # type: ignore
            f"⚠️ Received no response using Inference Client (model: '{self.model_name}')."
            f" Finish reason was: {e}"
        )
        return [None]

generate(inputs, num_generations=1, **kwargs)

Method to generate a list of responses asynchronously, returning the output synchronously awaiting for the response of each input sent to agenerate.

Source code in src/distilabel/llms/huggingface/inference_endpoints.py

@override
def generate(
    self,
    inputs: List["ChatType"],
    num_generations: int = 1,
    **kwargs: Any,
) -> List["GenerateOutput"]:
    """Method to generate a list of responses asynchronously, returning the output
    synchronously awaiting for the response of each input sent to `agenerate`.
    """

    async def agenerate(
        inputs: List["ChatType"], **kwargs: Any
    ) -> "GenerateOutput":
        """Internal function to parallelize the asynchronous generation of responses."""
        tasks = [
            asyncio.create_task(self.agenerate(input=input, **kwargs))
            for input in inputs
            for _ in range(num_generations)
        ]
        return [outputs[0] for outputs in await asyncio.gather(*tasks)]

    outputs = self.event_loop.run_until_complete(agenerate(inputs, **kwargs))
    return list(grouper(outputs, n=num_generations, incomplete="ignore"))

load()

Loads the either the AsyncInferenceClient or the AsyncOpenAI client to benefit from async requests, running the Hugging Face Inference Endpoint underneath via the /v1/chat/completions endpoint, exposed for the models running on TGI using the text-generation task.

Raises:

Type	Description
ImportError	if the openai Python client is not installed.
ImportError	if the huggingface-hub Python client is not installed.
ValueError	if the model is not currently deployed or is not running the TGI framework.
ImportError	if the transformers Python client is not installed.

Source code in src/distilabel/llms/huggingface/inference_endpoints.py

def load(self) -> None:  # noqa: C901
    """Loads the either the `AsyncInferenceClient` or the `AsyncOpenAI` client to benefit
    from async requests, running the Hugging Face Inference Endpoint underneath via the
    `/v1/chat/completions` endpoint, exposed for the models running on TGI using the
    `text-generation` task.

    Raises:
        ImportError: if the `openai` Python client is not installed.
        ImportError: if the `huggingface-hub` Python client is not installed.
        ValueError: if the model is not currently deployed or is not running the TGI framework.
        ImportError: if the `transformers` Python client is not installed.
    """
    super().load()

    try:
        from huggingface_hub import (
            AsyncInferenceClient,
            InferenceClient,
            get_inference_endpoint,
        )
    except ImportError as ie:
        raise ImportError(
            "Hugging Face Hub Python client is not installed. Please install it using"
            " `pip install huggingface-hub`."
        ) from ie

    if self.api_key is None:
        raise ValueError(
            f"To use `{self.__class__.__name__}` an API key must be provided via `api_key`"
            f" attribute or runtime parameter, or set the environment variable `{self._api_key_env_var}`."
        )

    if self.model_id is not None:
        client = InferenceClient()
        status = client.get_model_status(self.model_id)

        if (
            status.state not in {"Loadable", "Loaded"}
            and status.framework != "text-generation-inference"
        ):
            raise ValueError(
                f"Model {self.model_id} is not currently deployed or is not running the TGI framework"
            )

        self.base_url = client._resolve_url(
            model=self.model_id, task="text-generation"
        )

    if self.endpoint_name is not None:
        client = get_inference_endpoint(
            name=self.endpoint_name,
            namespace=self.endpoint_namespace,
            token=self.api_key.get_secret_value(),
        )
        if client.status in ["paused", "scaledToZero"]:
            client.resume().wait(timeout=300)
        elif client.status in ["initializing"]:
            client.wait(timeout=300)

        self.base_url = client.url
        self._model_name = client.repository

    if self.use_openai_client:
        try:
            from openai import AsyncOpenAI
        except ImportError as ie:
            raise ImportError(
                "OpenAI Python client is not installed. Please install it using"
                " `pip install openai`."
            ) from ie

        self._aclient = AsyncOpenAI(
            base_url=self.base_url,
            api_key=self.api_key.get_secret_value(),
            max_retries=6,
        )
    else:
        self._aclient = AsyncInferenceClient(
            model=self.base_url,
            token=self.api_key.get_secret_value(),
        )

    if self.tokenizer_id:
        try:
            from transformers import AutoTokenizer
        except ImportError as ie:
            raise ImportError(
                "Transformers Python client is not installed. Please install it using"
                " `pip install transformers`."
            ) from ie

        self._tokenizer = AutoTokenizer.from_pretrained(self.tokenizer_id)

only_one_of_model_id_endpoint_name_or_base_url_provided()

Validates that only one of model_id or endpoint_name is provided; and if base_url is also provided, a warning will be shown informing the user that the provided base_url will be ignored in favour of the dynamically calculated one..

Source code in src/distilabel/llms/huggingface/inference_endpoints.py

@model_validator(mode="after")  # type: ignore
def only_one_of_model_id_endpoint_name_or_base_url_provided(
    self,
) -> "InferenceEndpointsLLM":
    """Validates that only one of `model_id` or `endpoint_name` is provided; and if `base_url` is also
    provided, a warning will be shown informing the user that the provided `base_url` will be ignored in
    favour of the dynamically calculated one.."""

    if self.base_url and (self.model_id or self.endpoint_name):
        self._logger.warning(  # type: ignore
            f"Since the `base_url={self.base_url}` is available and either one of `model_id` or `endpoint_name`"
            " is also provided, the `base_url` will either be ignored or overwritten with the one generated"
            " from either of those args, for serverless or dedicated inference endpoints, respectively."
        )

    if self.base_url and not (self.model_id or self.endpoint_name):
        return self

    if self.model_id and not self.endpoint_name:
        return self

    if self.endpoint_name and not self.model_id:
        return self

    raise ValidationError(
        "Only one of `model_id` or `endpoint_name` must be provided. If `base_url` is provided too,"
        " it will be overwritten instead. Found `model_id`={self.model_id}, `endpoint_name`={self.endpoint_name},"
        f" and `base_url`={self.base_url}."
    )

Transformers

TransformersLLM

Bases: LLM, CudaDevicePlacementMixin

Hugging Face transformers library LLM implementation using the text generation pipeline.

Attributes:

Name	Type	Description
model	str	the model Hugging Face Hub repo id or a path to a directory containing the model weights and configuration files.
revision	str	if model refers to a Hugging Face Hub repository, then the revision (e.g. a branch name or a commit id) to use. Defaults to "main".
torch_dtype	str	the torch dtype to use for the model e.g. "float16", "float32", etc. Defaults to "auto".
trust_remote_code	bool	whether to trust or not remote (code in the Hugging Face Hub repository) code to load the model. Defaults to False.
model_kwargs	Optional[Dict[str, Any]]	additional dictionary of keyword arguments that will be passed to the from_pretrained method of the model.
tokenizer	Optional[str]	the tokenizer Hugging Face Hub repo id or a path to a directory containing the tokenizer config files. If not provided, the one associated to the model will be used. Defaults to None.
use_fast	bool	whether to use a fast tokenizer or not. Defaults to True.
chat_template	Optional[str]	a chat template that will be used to build the prompts before sending them to the model. If not provided, the chat template defined in the tokenizer config will be used. If not provided and the tokenizer doesn't have a chat template, then ChatML template will be used. Defaults to None.
device	Optional[Union[str, int]]	the name or index of the device where the model will be loaded. Defaults to None.
device_map	Optional[Union[str, Dict[str, Any]]]	a dictionary mapping each layer of the model to a device, or a mode like "sequential" or "auto". Defaults to None.
token	Optional[str]	the Hugging Face Hub token that will be used to authenticate to the Hugging Face Hub. If not provided, the HF_TOKEN environment or huggingface_hub package local configuration will be used. Defaults to None.

Source code in src/distilabel/llms/huggingface/transformers.py

class TransformersLLM(LLM, CudaDevicePlacementMixin):
    """Hugging Face `transformers` library LLM implementation using the text generation
    pipeline.

    Attributes:
        model: the model Hugging Face Hub repo id or a path to a directory containing the
            model weights and configuration files.
        revision: if `model` refers to a Hugging Face Hub repository, then the revision
            (e.g. a branch name or a commit id) to use. Defaults to `"main"`.
        torch_dtype: the torch dtype to use for the model e.g. "float16", "float32", etc.
            Defaults to `"auto"`.
        trust_remote_code: whether to trust or not remote (code in the Hugging Face Hub
            repository) code to load the model. Defaults to `False`.
        model_kwargs: additional dictionary of keyword arguments that will be passed to
            the `from_pretrained` method of the model.
        tokenizer: the tokenizer Hugging Face Hub repo id or a path to a directory containing
            the tokenizer config files. If not provided, the one associated to the `model`
            will be used. Defaults to `None`.
        use_fast: whether to use a fast tokenizer or not. Defaults to `True`.
        chat_template: a chat template that will be used to build the prompts before
            sending them to the model. If not provided, the chat template defined in the
            tokenizer config will be used. If not provided and the tokenizer doesn't have
            a chat template, then ChatML template will be used. Defaults to `None`.
        device: the name or index of the device where the model will be loaded. Defaults
            to `None`.
        device_map: a dictionary mapping each layer of the model to a device, or a mode
            like `"sequential"` or `"auto"`. Defaults to `None`.
        token: the Hugging Face Hub token that will be used to authenticate to the Hugging
            Face Hub. If not provided, the `HF_TOKEN` environment or `huggingface_hub` package
            local configuration will be used. Defaults to `None`.
    """

    model: str
    revision: str = "main"
    torch_dtype: str = "auto"
    trust_remote_code: bool = False
    model_kwargs: Optional[Dict[str, Any]] = None
    tokenizer: Optional[str] = None
    use_fast: bool = True
    chat_template: Optional[str] = None
    device: Optional[Union[str, int]] = None
    device_map: Optional[Union[str, Dict[str, Any]]] = None
    token: Optional[str] = None

    _pipeline: Optional["Pipeline"] = PrivateAttr(...)

    def load(self) -> None:
        """Loads the model and tokenizer and creates the text generation pipeline. In addition,
        it will configure the tokenizer chat template."""
        super().load()

        if self.device == "cuda":
            CudaDevicePlacementMixin.load(self)

        try:
            from transformers import pipeline
        except ImportError as ie:
            raise ImportError(
                "Transformers is not installed. Please install it using `pip install transformers`."
            ) from ie

        self._pipeline = pipeline(
            "text-generation",
            model=self.model,
            revision=self.revision,
            torch_dtype=self.torch_dtype,
            trust_remote_code=self.trust_remote_code,
            model_kwargs=self.model_kwargs or {},
            tokenizer=self.tokenizer or self.model,
            use_fast=self.use_fast,
            device=self.device,
            device_map=self.device_map,
            token=self.token or os.getenv("HF_TOKEN"),
            return_full_text=False,
        )

        if self.chat_template is not None:
            self._pipeline.tokenizer.chat_template = self.chat_template  # type: ignore
        elif (
            self._pipeline.tokenizer.chat_template is None  # type: ignore
            and self._pipeline.tokenizer.default_chat_template is None  # type: ignore
        ):
            self._pipeline.tokenizer.chat_template = CHATML_TEMPLATE  # type: ignore

    @property
    def model_name(self) -> str:
        """Returns the model name used for the LLM."""
        return self.model

    def prepare_input(self, input: "ChatType") -> str:
        """Prepares the input by applying the chat template to the input, which is formatted
        as an OpenAI conversation, and adding the generation prompt.
        """
        return self._pipeline.tokenizer.apply_chat_template(  # type: ignore
            input,  # type: ignore
            tokenize=False,
            add_generation_prompt=True,
        )

    @validate_call
    def generate(  # type: ignore
        self,
        inputs: List[ChatType],
        num_generations: int = 1,
        max_new_tokens: int = 128,
        temperature: float = 0.1,
        repetition_penalty: float = 1.1,
        top_p: float = 1.0,
        top_k: int = 0,
        do_sample: bool = True,
    ) -> List[GenerateOutput]:
        """Generates `num_generations` responses for each input using the text generation
        pipeline.

        Args:
            inputs: a list of inputs in chat format to generate responses for.
            num_generations: the number of generations to create per input. Defaults to
                `1`.
            max_new_tokens: the maximum number of new tokens that the model will generate.
                Defaults to `128`.
            temperature: the temperature to use for the generation. Defaults to `0.1`.
            repetition_penalty: the repetition penalty to use for the generation. Defaults
                to `1.1`.
            top_p: the top-p value to use for the generation. Defaults to `1.0`.
            top_k: the top-k value to use for the generation. Defaults to `0`.
            do_sample: whether to use sampling or not. Defaults to `True`.

        Returns:
            A list of lists of strings containing the generated responses for each input.
        """
        outputs: List[List[Dict[str, str]]] = self._pipeline(  # type: ignore
            [self.prepare_input(input=input) for input in inputs],
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            repetition_penalty=repetition_penalty,
            top_p=top_p,
            top_k=top_k,
            do_sample=do_sample,
            num_return_sequences=num_generations,
        )
        return [
            [generation["generated_text"] for generation in output]
            for output in outputs
        ]

    def get_last_hidden_states(self, inputs: List["ChatType"]) -> List["HiddenState"]:
        """Gets the last `hidden_states` of the model for the given inputs. It doesn't
        execute the task head.

        Args:
            inputs: a list of inputs in chat format to generate the embeddings for.

        Returns:
            A list containing the last hidden state for each sequence using a NumPy array
            with shape [num_tokens, hidden_size].
        """
        model: "PreTrainedModel" = (
            self._pipeline.model.model  # type: ignore
            if hasattr(self._pipeline.model, "model")  # type: ignore
            else next(self._pipeline.model.children())  # type: ignore
        )
        tokenizer: "PreTrainedTokenizer" = self._pipeline.tokenizer  # type: ignore
        input_ids = tokenizer(
            [self.prepare_input(input) for input in inputs],  # type: ignore
            return_tensors="pt",
            padding=True,
        ).to(model.device)
        last_hidden_states = model(**input_ids)["last_hidden_state"]

        return [
            seq_last_hidden_state[attention_mask.bool(), :].detach().cpu().numpy()
            for seq_last_hidden_state, attention_mask in zip(
                last_hidden_states,
                input_ids["attention_mask"],  # type: ignore
            )
        ]

model_name: str property

Returns the model name used for the LLM.

generate(inputs, num_generations=1, max_new_tokens=128, temperature=0.1, repetition_penalty=1.1, top_p=1.0, top_k=0, do_sample=True)

Generates num_generations responses for each input using the text generation pipeline.

Parameters:

Name	Type	Description	Default
inputs	List[ChatType]	a list of inputs in chat format to generate responses for.	required
num_generations	int	the number of generations to create per input. Defaults to 1.	1
max_new_tokens	int	the maximum number of new tokens that the model will generate. Defaults to 128.	128
temperature	float	the temperature to use for the generation. Defaults to 0.1.	0.1
repetition_penalty	float	the repetition penalty to use for the generation. Defaults to 1.1.	1.1
top_p	float	the top-p value to use for the generation. Defaults to 1.0.	1.0
top_k	int	the top-k value to use for the generation. Defaults to 0.	0
do_sample	bool	whether to use sampling or not. Defaults to True.	True

Returns:

Type	Description
List[GenerateOutput]	A list of lists of strings containing the generated responses for each input.

Source code in src/distilabel/llms/huggingface/transformers.py

@validate_call
def generate(  # type: ignore
    self,
    inputs: List[ChatType],
    num_generations: int = 1,
    max_new_tokens: int = 128,
    temperature: float = 0.1,
    repetition_penalty: float = 1.1,
    top_p: float = 1.0,
    top_k: int = 0,
    do_sample: bool = True,
) -> List[GenerateOutput]:
    """Generates `num_generations` responses for each input using the text generation
    pipeline.

    Args:
        inputs: a list of inputs in chat format to generate responses for.
        num_generations: the number of generations to create per input. Defaults to
            `1`.
        max_new_tokens: the maximum number of new tokens that the model will generate.
            Defaults to `128`.
        temperature: the temperature to use for the generation. Defaults to `0.1`.
        repetition_penalty: the repetition penalty to use for the generation. Defaults
            to `1.1`.
        top_p: the top-p value to use for the generation. Defaults to `1.0`.
        top_k: the top-k value to use for the generation. Defaults to `0`.
        do_sample: whether to use sampling or not. Defaults to `True`.

    Returns:
        A list of lists of strings containing the generated responses for each input.
    """
    outputs: List[List[Dict[str, str]]] = self._pipeline(  # type: ignore
        [self.prepare_input(input=input) for input in inputs],
        max_new_tokens=max_new_tokens,
        temperature=temperature,
        repetition_penalty=repetition_penalty,
        top_p=top_p,
        top_k=top_k,
        do_sample=do_sample,
        num_return_sequences=num_generations,
    )
    return [
        [generation["generated_text"] for generation in output]
        for output in outputs
    ]

get_last_hidden_states(inputs)

Gets the last hidden_states of the model for the given inputs. It doesn't execute the task head.

Parameters:

Name	Type	Description	Default
inputs	List[ChatType]	a list of inputs in chat format to generate the embeddings for.	required

Returns:

Type	Description
List[HiddenState]	A list containing the last hidden state for each sequence using a NumPy array
List[HiddenState]	with shape [num_tokens, hidden_size].

Source code in src/distilabel/llms/huggingface/transformers.py

def get_last_hidden_states(self, inputs: List["ChatType"]) -> List["HiddenState"]:
    """Gets the last `hidden_states` of the model for the given inputs. It doesn't
    execute the task head.

    Args:
        inputs: a list of inputs in chat format to generate the embeddings for.

    Returns:
        A list containing the last hidden state for each sequence using a NumPy array
        with shape [num_tokens, hidden_size].
    """
    model: "PreTrainedModel" = (
        self._pipeline.model.model  # type: ignore
        if hasattr(self._pipeline.model, "model")  # type: ignore
        else next(self._pipeline.model.children())  # type: ignore
    )
    tokenizer: "PreTrainedTokenizer" = self._pipeline.tokenizer  # type: ignore
    input_ids = tokenizer(
        [self.prepare_input(input) for input in inputs],  # type: ignore
        return_tensors="pt",
        padding=True,
    ).to(model.device)
    last_hidden_states = model(**input_ids)["last_hidden_state"]

    return [
        seq_last_hidden_state[attention_mask.bool(), :].detach().cpu().numpy()
        for seq_last_hidden_state, attention_mask in zip(
            last_hidden_states,
            input_ids["attention_mask"],  # type: ignore
        )
    ]

load()

Loads the model and tokenizer and creates the text generation pipeline. In addition, it will configure the tokenizer chat template.

Source code in src/distilabel/llms/huggingface/transformers.py

def load(self) -> None:
    """Loads the model and tokenizer and creates the text generation pipeline. In addition,
    it will configure the tokenizer chat template."""
    super().load()

    if self.device == "cuda":
        CudaDevicePlacementMixin.load(self)

    try:
        from transformers import pipeline
    except ImportError as ie:
        raise ImportError(
            "Transformers is not installed. Please install it using `pip install transformers`."
        ) from ie

    self._pipeline = pipeline(
        "text-generation",
        model=self.model,
        revision=self.revision,
        torch_dtype=self.torch_dtype,
        trust_remote_code=self.trust_remote_code,
        model_kwargs=self.model_kwargs or {},
        tokenizer=self.tokenizer or self.model,
        use_fast=self.use_fast,
        device=self.device,
        device_map=self.device_map,
        token=self.token or os.getenv("HF_TOKEN"),
        return_full_text=False,
    )

    if self.chat_template is not None:
        self._pipeline.tokenizer.chat_template = self.chat_template  # type: ignore
    elif (
        self._pipeline.tokenizer.chat_template is None  # type: ignore
        and self._pipeline.tokenizer.default_chat_template is None  # type: ignore
    ):
        self._pipeline.tokenizer.chat_template = CHATML_TEMPLATE  # type: ignore

prepare_input(input)

Prepares the input by applying the chat template to the input, which is formatted as an OpenAI conversation, and adding the generation prompt.

Source code in src/distilabel/llms/huggingface/transformers.py

def prepare_input(self, input: "ChatType") -> str:
    """Prepares the input by applying the chat template to the input, which is formatted
    as an OpenAI conversation, and adding the generation prompt.
    """
    return self._pipeline.tokenizer.apply_chat_template(  # type: ignore
        input,  # type: ignore
        tokenize=False,
        add_generation_prompt=True,
    )