unitxt.inference module

class unitxt.inference.HFPipelineBasedInferenceEngine(__tags__: ~typing.Dict[str, str] = {}, model_name: str, max_new_tokens: int, use_fp16: bool = True)

Bases: InferenceEngine, PackageRequirementsMixin

class unitxt.inference.IbmGenAiInferenceEngine(__tags__: ~typing.Dict[str, str] = {}, label: str = 'ibm_genai', model_name: str, parameters: ~unitxt.inference.IbmGenAiInferenceEngineParams)

Bases: InferenceEngine, PackageRequirementsMixin

class unitxt.inference.IbmGenAiInferenceEngineParams(__tags__: Dict[str, str] = {}, decoding_method: Literal['greedy', 'sample'] | None = None, max_new_tokens: int | None = None, min_new_tokens: int | None = None, random_seed: int | None = None, repetition_penalty: float | None = None, stop_sequences: List[str] | None = None, temperature: float | None = None, top_k: int | None = None, top_p: float | None = None, typical_p: float | None = None)

Bases: Artifact

class unitxt.inference.InferenceEngine(__tags__: Dict[str, str] = {})

Bases: ABC, Artifact

Abstract base class for inference.

class unitxt.inference.MockInferenceEngine(__tags__: ~typing.Dict[str, str] = {}, model_name: str)

Bases: InferenceEngine

class unitxt.inference.OpenAiInferenceEngine(__tags__: ~typing.Dict[str, str] = {}, label: str = 'openai', model_name: str, parameters: ~unitxt.inference.OpenAiInferenceEngineParams)

Bases: InferenceEngine, PackageRequirementsMixin

class unitxt.inference.OpenAiInferenceEngineParams(__tags__: Dict[str, str] = {}, frequency_penalty: float | None = None, presence_penalty: float | None = None, max_tokens: int | None = None, seed: int | None = None, stop: str | None | List[str] = None, temperature: float | None = None, top_p: float | None = None)

Bases: Artifact