Hub Python Library documentation
Jenis inferensi
Jenis inferensi
Halaman ini mencantumkan tipe (misalnya dataclasses) yang tersedia untuk setiap tugas yang didukung di Hugging Face Hub. Setiap tugas ditentukan menggunakan skema JSON, dan tipe-tipe tersebut dihasilkan dari skema ini - dengan beberapa penyesuaian karena persyaratan Python. Kunjungi @huggingface.js/tasks untuk menemukan skema JSON untuk setiap tugas.
Bagian ini dari lib masih dalam tahap pengembangan dan akan ditingkatkan dalam rilis mendatang.
audio_classification
kelas huggingface_hub.AudioClassificationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.audio_classification.AudioClassificationParameters | None = None )
Input untuk inferensi Klasifikasi Audio
Output untuk inferensi Klasifikasi Audio
kelas huggingface_hub.AudioClassificationParameters
< source >( function_to_apply: typing.Optional[ForwardRef('AudioClassificationOutputTransform')] = Nonetop_k: int | None = None )
Parameter inferensi tambahan untuk Klasifikasi Audio
audio_to_audio
Input untuk inferensi Audio ke Audio
kelas huggingface_hub.AudioToAudioOutputElement
< source >( blob: typing.Anycontent_type: strlabel: str )
Output inferensi untuk tugas Audio ke Audio File audio yang dihasilkan beserta labelnya.
automatic_speech_recognition
kelas huggingface_hub.AutomaticSpeechRecognitionGenerationParameters
< source >( do_sample: bool | None = Noneearly_stopping: typing.Union[bool, ForwardRef('AutomaticSpeechRecognitionEarlyStoppingEnum'), NoneType] = Noneepsilon_cutoff: float | None = Noneeta_cutoff: float | None = Nonemax_length: int | None = Nonemax_new_tokens: int | None = Nonemin_length: int | None = Nonemin_new_tokens: int | None = Nonenum_beam_groups: int | None = Nonenum_beams: int | None = Nonepenalty_alpha: float | None = Nonetemperature: float | None = Nonetop_k: int | None = Nonetop_p: float | None = Nonetypical_p: float | None = Noneuse_cache: bool | None = None )
Parametrisasi proses generasi teks
kelas huggingface_hub.AutomaticSpeechRecognitionInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.automatic_speech_recognition.AutomaticSpeechRecognitionParameters | None = None )
Input untuk inferensi Automatic Speech Recognition
kelas huggingface_hub.AutomaticSpeechRecognitionOutput
< source >( text: strchunks: list[huggingface_hub.inference._generated.types.automatic_speech_recognition.AutomaticSpeechRecognitionOutputChunk] | None = None )
Output inferensi untuk tugas Automatic Speech Recognition
kelas huggingface_hub.AutomaticSpeechRecognitionParameters
< source >( generation_parameters: huggingface_hub.inference._generated.types.automatic_speech_recognition.AutomaticSpeechRecognitionGenerationParameters | None = Nonereturn_timestamps: bool | None = None )
Parameter inferensi tambahan untuk Automatic Speech Recognition
chat_completion
kelas huggingface_hub.ChatCompletionInput
< source >( messages: listfrequency_penalty: float | None = Nonelogit_bias: list[float] | None = Nonelogprobs: bool | None = Nonemax_tokens: int | None = Nonemodel: str | None = Nonen: int | None = Nonepresence_penalty: float | None = Noneresponse_format: typing.Union[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputResponseFormatText, huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputResponseFormatJSONSchema, huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputResponseFormatJSONObject, NoneType] = Noneseed: int | None = Nonestop: list[str] | None = Nonestream: bool | None = Nonestream_options: huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputStreamOptions | None = Nonetemperature: float | None = Nonetool_choice: typing.Union[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputToolChoiceClass, ForwardRef('ChatCompletionInputToolChoiceEnum'), NoneType] = Nonetool_prompt: str | None = Nonetools: list[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputTool] | None = Nonetop_logprobs: int | None = Nonetop_p: float | None = None )
Input Penyelesaian Chat. Dibuat otomatis dari spesifikasi TGI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
kelas huggingface_hub.ChatCompletionInputFunctionDefinition
< source >( name: strparameters: typing.Anydescription: str | None = None )
kelas huggingface_hub.ChatCompletionInputJSONSchema
< source >( name: strdescription: str | None = Noneschema: dict[str, object] | None = Nonestrict: bool | None = None )
kelas huggingface_hub.ChatCompletionInputMessage
< source >( role: strcontent: list[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputMessageChunk] | str | None = Nonename: str | None = Nonetool_calls: list[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputToolCall] | None = None )
kelas huggingface_hub.ChatCompletionInputMessageChunk
< source >( type: ChatCompletionInputMessageChunkTypeimage_url: huggingface_hub.inference._generated.types.chat_completion.ChatCompletionInputURL | None = Nonetext: str | None = None )
kelas huggingface_hub.ChatCompletionInputResponseFormatJSONObject
< source >( type: typing.Literal['json_object'] )
kelas huggingface_hub.ChatCompletionInputResponseFormatJSONSchema
< source >( type: typing.Literal['json_schema']json_schema: ChatCompletionInputJSONSchema )
kelas huggingface_hub.ChatCompletionInputResponseFormatText
< source >( type: typing.Literal['text'] )
kelas huggingface_hub.ChatCompletionInputStreamOptions
< source >( include_usage: bool | None = None )
kelas huggingface_hub.ChatCompletionInputTool
< source >( function: ChatCompletionInputFunctionDefinitiontype: str )
kelas huggingface_hub.ChatCompletionInputToolCall
< source >( function: ChatCompletionInputFunctionDefinitionid: strtype: str )
kelas huggingface_hub.ChatCompletionInputToolChoiceClass
< source >( function: ChatCompletionInputFunctionName )
kelas huggingface_hub.ChatCompletionOutput
< source >( choices: listcreated: intid: strmodel: strsystem_fingerprint: strusage: ChatCompletionOutputUsage )
Output Penyelesaian Chat. Dibuat otomatis dari spesifikasi TGI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
kelas huggingface_hub.ChatCompletionOutputComplete
< source >( finish_reason: strindex: intmessage: ChatCompletionOutputMessagelogprobs: huggingface_hub.inference._generated.types.chat_completion.ChatCompletionOutputLogprobs | None = None )
kelas huggingface_hub.ChatCompletionOutputFunctionDefinition
< source >( arguments: strname: strdescription: str | None = None )
kelas huggingface_hub.ChatCompletionOutputLogprob
< source >( logprob: floattoken: strtop_logprobs: list )
kelas huggingface_hub.ChatCompletionOutputMessage
< source >( role: strcontent: str | None = Nonereasoning: str | None = Nonetool_call_id: str | None = Nonetool_calls: list[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionOutputToolCall] | None = None )
kelas huggingface_hub.ChatCompletionOutputToolCall
< source >( function: ChatCompletionOutputFunctionDefinitionid: strtype: str )
kelas huggingface_hub.ChatCompletionOutputUsage
< source >( completion_tokens: intprompt_tokens: inttotal_tokens: int )
kelas huggingface_hub.ChatCompletionStreamOutput
< source >( choices: listcreated: intid: strmodel: strsystem_fingerprint: strusage: huggingface_hub.inference._generated.types.chat_completion.ChatCompletionStreamOutputUsage | None = None )
Output Stream Penyelesaian Chat. Dibuat otomatis dari spesifikasi TGI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
kelas huggingface_hub.ChatCompletionStreamOutputChoice
< source >( delta: ChatCompletionStreamOutputDeltaindex: intfinish_reason: str | None = Nonelogprobs: huggingface_hub.inference._generated.types.chat_completion.ChatCompletionStreamOutputLogprobs | None = None )
kelas huggingface_hub.ChatCompletionStreamOutputDelta
< source >( role: strcontent: str | None = Nonereasoning: str | None = Nonetool_call_id: str | None = Nonetool_calls: list[huggingface_hub.inference._generated.types.chat_completion.ChatCompletionStreamOutputDeltaToolCall] | None = None )
kelas huggingface_hub.ChatCompletionStreamOutputDeltaToolCall
< source >( function: ChatCompletionStreamOutputFunctionid: strindex: inttype: str )
kelas huggingface_hub.ChatCompletionStreamOutputFunction
< source >( arguments: strname: str | None = None )
kelas huggingface_hub.ChatCompletionStreamOutputLogprob
< source >( logprob: floattoken: strtop_logprobs: list )
kelas huggingface_hub.ChatCompletionStreamOutputUsage
< source >( completion_tokens: intprompt_tokens: inttotal_tokens: int )
depth_estimation
kelas huggingface_hub.DepthEstimationInput
< source >( inputs: typing.Anyparameters: dict[str, typing.Any] | None = None )
Input untuk inferensi Estimasi Kedalaman
kelas huggingface_hub.DepthEstimationOutput
< source >( depth: typing.Anypredicted_depth: typing.Any )
Output inferensi untuk tugas Estimasi Kedalaman
document_question_answering
kelas huggingface_hub.DocumentQuestionAnsweringInput
< source >( inputs: DocumentQuestionAnsweringInputDataparameters: huggingface_hub.inference._generated.types.document_question_answering.DocumentQuestionAnsweringParameters | None = None )
Input untuk inferensi Document Question Answering
kelas huggingface_hub.DocumentQuestionAnsweringInputData
< source >( image: typing.Anyquestion: str )
Satu pasangan (dokumen, pertanyaan) untuk dijawab
kelas huggingface_hub.DocumentQuestionAnsweringOutputElement
< source >( answer: strend: intscore: floatstart: int )
Output inferensi untuk tugas Document Question Answering
kelas huggingface_hub.DocumentQuestionAnsweringParameters
< source >( doc_stride: int | None = Nonehandle_impossible_answer: bool | None = Nonelang: str | None = Nonemax_answer_len: int | None = Nonemax_question_len: int | None = Nonemax_seq_len: int | None = Nonetop_k: int | None = Noneword_boxes: list[list[float] | str] | None = None )
Parameter inferensi tambahan untuk Document Question Answering
feature_extraction
kelas huggingface_hub.FeatureExtractionInput
< source >( inputs: list[str] | strnormalize: bool | None = Noneprompt_name: str | None = Nonetruncate: bool | None = Nonetruncation_direction: typing.Optional[ForwardRef('FeatureExtractionInputTruncationDirection')] = None )
Input Ekstraksi Fitur. Dibuat otomatis dari spesifikasi TEI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tei-import.ts.
fill_mask
kelas huggingface_hub.FillMaskInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.fill_mask.FillMaskParameters | None = None )
Input untuk inferensi Fill Mask
kelas huggingface_hub.FillMaskOutputElement
< source >( score: floatsequence: strtoken: inttoken_str: typing.Anyfill_mask_output_token_str: str | None = None )
Output inferensi untuk tugas Fill Mask
kelas huggingface_hub.FillMaskParameters
< source >( targets: list[str] | None = Nonetop_k: int | None = None )
Parameter inferensi tambahan untuk Fill Mask
image_classification
kelas huggingface_hub.ImageClassificationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.image_classification.ImageClassificationParameters | None = None )
Input untuk inferensi Klasifikasi Gambar
Output inferensi untuk tugas Klasifikasi Gambar
kelas huggingface_hub.ImageClassificationParameters
< source >( function_to_apply: typing.Optional[ForwardRef('ImageClassificationOutputTransform')] = Nonetop_k: int | None = None )
Parameter inferensi tambahan untuk Klasifikasi Gambar
image_segmentation
kelas huggingface_hub.ImageSegmentationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.image_segmentation.ImageSegmentationParameters | None = None )
Input untuk inferensi Segmentasi Gambar
kelas huggingface_hub.ImageSegmentationOutputElement
< source >( label: strmask: strscore: float | None = None )
Output inferensi untuk tugas Segmentasi Gambar Mask / segmen yang diprediksi
kelas huggingface_hub.ImageSegmentationParameters
< source >( mask_threshold: float | None = Noneoverlap_mask_area_threshold: float | None = Nonesubtask: typing.Optional[ForwardRef('ImageSegmentationSubtask')] = Nonethreshold: float | None = None )
Parameter inferensi tambahan untuk Segmentasi Gambar
image_text_to_image
kelas huggingface_hub.ImageTextToImageInput
< source >( inputs: str | None = Noneparameters: huggingface_hub.inference._generated.types.image_text_to_image.ImageTextToImageParameters | None = None )
Input untuk inferensi Image Text To Image. Salah satu dari inputs (image) atau prompt (di parameters) harus disediakan, atau keduanya.
Output inferensi untuk tugas Image Text To Image
kelas huggingface_hub.ImageTextToImageParameters
< source >( guidance_scale: float | None = Nonenegative_prompt: str | None = Nonenum_inference_steps: int | None = Noneprompt: str | None = Noneseed: int | None = Nonetarget_size: huggingface_hub.inference._generated.types.image_text_to_image.ImageTextToImageTargetSize | None = None )
Parameter inferensi tambahan untuk Image Text To Image
Ukuran gambar keluaran dalam piksel. Parameter ini hanya didukung oleh beberapa penyedia dan untuk model tertentu. Parameter ini akan diabaikan jika tidak didukung.
image_text_to_video
kelas huggingface_hub.ImageTextToVideoInput
< source >( inputs: str | None = Noneparameters: huggingface_hub.inference._generated.types.image_text_to_video.ImageTextToVideoParameters | None = None )
Input untuk inferensi Image Text To Video. Salah satu dari inputs (image) atau prompt (di parameters) harus disediakan, atau keduanya.
Output inferensi untuk tugas Image Text To Video
kelas huggingface_hub.ImageTextToVideoParameters
< source >( guidance_scale: float | None = Nonenegative_prompt: str | None = Nonenum_frames: float | None = Nonenum_inference_steps: int | None = Noneprompt: str | None = Noneseed: int | None = Nonetarget_size: huggingface_hub.inference._generated.types.image_text_to_video.ImageTextToVideoTargetSize | None = None )
Parameter inferensi tambahan untuk Image Text To Video
Ukuran dalam piksel dari bingkai video keluaran.
image_to_image
kelas huggingface_hub.ImageToImageInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.image_to_image.ImageToImageParameters | None = None )
Inputs for Image To Image inference
Output inferensi untuk tugas Image To Image
kelas huggingface_hub.ImageToImageParameters
< source >( guidance_scale: float | None = Nonenegative_prompt: str | None = Nonenum_inference_steps: int | None = Noneprompt: str | None = Nonetarget_size: huggingface_hub.inference._generated.types.image_to_image.ImageToImageTargetSize | None = None )
Parameter inferensi tambahan untuk Image To Image
Ukuran gambar keluaran dalam piksel. Parameter ini hanya didukung oleh beberapa penyedia dan untuk model tertentu. Parameter ini akan diabaikan jika tidak didukung.
image_to_text
kelas huggingface_hub.ImageToTextGenerationParameters
< source >( do_sample: bool | None = Noneearly_stopping: typing.Union[bool, ForwardRef('ImageToTextEarlyStoppingEnum'), NoneType] = Noneepsilon_cutoff: float | None = Noneeta_cutoff: float | None = Nonemax_length: int | None = Nonemax_new_tokens: int | None = Nonemin_length: int | None = Nonemin_new_tokens: int | None = Nonenum_beam_groups: int | None = Nonenum_beams: int | None = Nonepenalty_alpha: float | None = Nonetemperature: float | None = Nonetop_k: int | None = Nonetop_p: float | None = Nonetypical_p: float | None = Noneuse_cache: bool | None = None )
Parametrisasi proses generasi teks
kelas huggingface_hub.ImageToTextInput
< source >( inputs: typing.Anyparameters: huggingface_hub.inference._generated.types.image_to_text.ImageToTextParameters | None = None )
Input untuk inferensi Gambar ke Teks
kelas huggingface_hub.ImageToTextOutput
< source >( generated_text: typing.Anyimage_to_text_output_generated_text: str | None = None )
Output inferensi untuk tugas Image To Text
kelas huggingface_hub.ImageToTextParameters
< source >( generation_parameters: huggingface_hub.inference._generated.types.image_to_text.ImageToTextGenerationParameters | None = Nonemax_new_tokens: int | None = None )
Parameter inferensi tambahan untuk Image To Text
image_to_video
kelas huggingface_hub.ImageToVideoInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.image_to_video.ImageToVideoParameters | None = None )
Inputs for Image To Video inference
Output inferensi untuk tugas Image To Video
kelas huggingface_hub.ImageToVideoParameters
< source >( guidance_scale: float | None = Nonenegative_prompt: str | None = Nonenum_frames: float | None = Nonenum_inference_steps: int | None = Noneprompt: str | None = Noneseed: int | None = Nonetarget_size: huggingface_hub.inference._generated.types.image_to_video.ImageToVideoTargetSize | None = None )
Parameter inferensi tambahan untuk Image To Video
Ukuran dalam piksel dari bingkai video keluaran.
object_detection
kelas huggingface_hub.ObjectDetectionBoundingBox
< source >( xmax: intxmin: intymax: intymin: int )
Kotak batas yang diprediksi. Koordinat relatif terhadap sudut kiri atas gambar input.
kelas huggingface_hub.ObjectDetectionInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.object_detection.ObjectDetectionParameters | None = None )
Input untuk inferensi Object Detection
kelas huggingface_hub.ObjectDetectionOutputElement
< source >( box: ObjectDetectionBoundingBoxlabel: strscore: float )
Output inferensi untuk tugas Object Detection
Parameter inferensi tambahan untuk Object Detection
question_answering
kelas huggingface_hub.QuestionAnsweringInput
< source >( inputs: QuestionAnsweringInputDataparameters: huggingface_hub.inference._generated.types.question_answering.QuestionAnsweringParameters | None = None )
Input untuk inferensi Question Answering
Satu pasangan (konteks, pertanyaan) untuk dijawab
kelas huggingface_hub.QuestionAnsweringOutputElement
< source >( answer: strend: intscore: floatstart: int )
Output inferensi untuk tugas Question Answering
kelas huggingface_hub.QuestionAnsweringParameters
< source >( align_to_words: bool | None = Nonedoc_stride: int | None = Nonehandle_impossible_answer: bool | None = Nonemax_answer_len: int | None = Nonemax_question_len: int | None = Nonemax_seq_len: int | None = Nonetop_k: int | None = None )
Parameter inferensi tambahan untuk Question Answering
sentence_similarity
kelas huggingface_hub.SentenceSimilarityInput
< source >( inputs: SentenceSimilarityInputDataparameters: dict[str, typing.Any] | None = None )
Input untuk inferensi kemiripan kalimat
kelas huggingface_hub.SentenceSimilarityInputData
< source >( sentences: listsource_sentence: str )
ringkasan
kelas huggingface_hub.SummarizationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.summarization.SummarizationParameters | None = None )
Input untuk inferensi Ringkasan
Output inferensi untuk tugas Ringkasan
kelas huggingface_hub.SummarizationParameters
< source >( clean_up_tokenization_spaces: bool | None = Nonegenerate_parameters: dict[str, typing.Any] | None = Nonetruncation: typing.Optional[ForwardRef('SummarizationTruncationStrategy')] = None )
Parameter inferensi tambahan untuk ringkasan.
table_question_answering
kelas huggingface_hub.TableQuestionAnsweringInput
< source >( inputs: TableQuestionAnsweringInputDataparameters: huggingface_hub.inference._generated.types.table_question_answering.TableQuestionAnsweringParameters | None = None )
Input untuk inferensi Table Question Answering
Satu pasangan (tabel, pertanyaan) untuk dijawab
kelas huggingface_hub.TableQuestionAnsweringOutputElement
< source >( answer: strcells: listcoordinates: listaggregator: str | None = None )
Output inferensi untuk tugas Table Question Answering
kelas huggingface_hub.TableQuestionAnsweringParameters
< source >( padding: typing.Optional[ForwardRef('Padding')] = Nonesequential: bool | None = Nonetruncation: bool | None = None )
Parameter inferensi tambahan untuk Table Question Answering
text2text_generation
kelas huggingface_hub.Text2TextGenerationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text2text_generation.Text2TextGenerationParameters | None = None )
Input untuk inferensi generasi Text2text
kelas huggingface_hub.Text2TextGenerationOutput
< source >( generated_text: typing.Anytext2_text_generation_output_generated_text: str | None = None )
Output inferensi untuk tugas Text2text Generation
kelas huggingface_hub.Text2TextGenerationParameters
< source >( clean_up_tokenization_spaces: bool | None = Nonegenerate_parameters: dict[str, typing.Any] | None = Nonetruncation: typing.Optional[ForwardRef('Text2TextGenerationTruncationStrategy')] = None )
Parameter inferensi tambahan untuk Generasi Text2text
text_classification
kelas huggingface_hub.TextClassificationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text_classification.TextClassificationParameters | None = None )
Input untuk inferensi Klasifikasi Teks
Output inferensi untuk tugas Klasifikasi Teks
kelas huggingface_hub.TextClassificationParameters
< source >( function_to_apply: typing.Optional[ForwardRef('TextClassificationOutputTransform')] = Nonetop_k: int | None = None )
Parameter inferensi tambahan untuk Klasifikasi Teks
text_generation
kelas huggingface_hub.TextGenerationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text_generation.TextGenerationInputGenerateParameters | None = Nonestream: bool | None = None )
Input Generasi Teks. Dibuat otomatis dari spesifikasi TGI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
kelas huggingface_hub.TextGenerationInputGenerateParameters
< source >( adapter_id: str | None = Nonebest_of: int | None = Nonedecoder_input_details: bool | None = Nonedetails: bool | None = Nonedo_sample: bool | None = Nonefrequency_penalty: float | None = Nonegrammar: huggingface_hub.inference._generated.types.text_generation.TextGenerationInputGrammarType | None = Nonemax_new_tokens: int | None = Nonerepetition_penalty: float | None = Nonereturn_full_text: bool | None = Noneseed: int | None = Nonestop: list[str] | None = Nonetemperature: float | None = Nonetop_k: int | None = Nonetop_n_tokens: int | None = Nonetop_p: float | None = Nonetruncate: int | None = Nonetypical_p: float | None = Nonewatermark: bool | None = None )
kelas huggingface_hub.TextGenerationOutput
< source >( generated_text: strdetails: huggingface_hub.inference._generated.types.text_generation.TextGenerationOutputDetails | None = None )
Output Generasi Teks. Dibuat otomatis dari spesifikasi TGI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
kelas huggingface_hub.TextGenerationOutputBestOfSequence
< source >( finish_reason: TextGenerationOutputFinishReasongenerated_text: strgenerated_tokens: intprefill: listtokens: listseed: int | None = Nonetop_tokens: list[list[huggingface_hub.inference._generated.types.text_generation.TextGenerationOutputToken]] | None = None )
kelas huggingface_hub.TextGenerationOutputDetails
< source >( finish_reason: TextGenerationOutputFinishReasongenerated_tokens: intprefill: listtokens: listbest_of_sequences: list[huggingface_hub.inference._generated.types.text_generation.TextGenerationOutputBestOfSequence] | None = Noneseed: int | None = Nonetop_tokens: list[list[huggingface_hub.inference._generated.types.text_generation.TextGenerationOutputToken]] | None = None )
kelas huggingface_hub.TextGenerationOutputPrefillToken
< source >( id: intlogprob: floattext: str )
kelas huggingface_hub.TextGenerationOutputToken
< source >( id: intlogprob: floatspecial: booltext: str )
kelas huggingface_hub.TextGenerationStreamOutput
< source >( index: inttoken: TextGenerationStreamOutputTokendetails: huggingface_hub.inference._generated.types.text_generation.TextGenerationStreamOutputStreamDetails | None = Nonegenerated_text: str | None = Nonetop_tokens: list[huggingface_hub.inference._generated.types.text_generation.TextGenerationStreamOutputToken] | None = None )
Output Stream Teks Generatif. Dibuat otomatis dari spesifikasi TGI. Untuk detail lebih lanjut, lihat https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
kelas huggingface_hub.TextGenerationStreamOutputStreamDetails
< source >( finish_reason: TextGenerationOutputFinishReasongenerated_tokens: intinput_length: intseed: int | None = None )
kelas huggingface_hub.TextGenerationStreamOutputToken
< source >( id: intlogprob: floatspecial: booltext: str )
text_to_audio
kelas huggingface_hub.TextToAudioGenerationParameters
< source >( do_sample: bool | None = Noneearly_stopping: typing.Union[bool, ForwardRef('TextToAudioEarlyStoppingEnum'), NoneType] = Noneepsilon_cutoff: float | None = Noneeta_cutoff: float | None = Nonemax_length: int | None = Nonemax_new_tokens: int | None = Nonemin_length: int | None = Nonemin_new_tokens: int | None = Nonenum_beam_groups: int | None = Nonenum_beams: int | None = Nonepenalty_alpha: float | None = Nonetemperature: float | None = Nonetop_k: int | None = Nonetop_p: float | None = Nonetypical_p: float | None = Noneuse_cache: bool | None = None )
Parametrisasi proses generasi teks
kelas huggingface_hub.TextToAudioInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text_to_audio.TextToAudioParameters | None = None )
Input untuk inferensi Teks ke Audio
Output inferensi untuk tugas Text To Audio
kelas huggingface_hub.TextToAudioParameters
< source >( generation_parameters: huggingface_hub.inference._generated.types.text_to_audio.TextToAudioGenerationParameters | None = None )
Parameter inferensi tambahan untuk Text To Audio
text_to_image
kelas huggingface_hub.TextToImageInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text_to_image.TextToImageParameters | None = None )
Input untuk inferensi Teks Ke Gambar
Output inferensi untuk tugas Text To Image
kelas huggingface_hub.TextToImageParameters
< source >( guidance_scale: float | None = Noneheight: int | None = Nonenegative_prompt: str | None = Nonenum_inference_steps: int | None = Nonescheduler: str | None = Noneseed: int | None = Nonewidth: int | None = None )
Parameter inferensi tambahan untuk Teks ke Gambar
text_to_speech
kelas huggingface_hub.TextToSpeechGenerationParameters
< source >( do_sample: bool | None = Noneearly_stopping: typing.Union[bool, ForwardRef('TextToSpeechEarlyStoppingEnum'), NoneType] = Noneepsilon_cutoff: float | None = Noneeta_cutoff: float | None = Nonemax_length: int | None = Nonemax_new_tokens: int | None = Nonemin_length: int | None = Nonemin_new_tokens: int | None = Nonenum_beam_groups: int | None = Nonenum_beams: int | None = Nonepenalty_alpha: float | None = Nonetemperature: float | None = Nonetop_k: int | None = Nonetop_p: float | None = Nonetypical_p: float | None = Noneuse_cache: bool | None = None )
Parametrisasi proses generasi teks
kelas huggingface_hub.TextToSpeechInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text_to_speech.TextToSpeechParameters | None = None )
Inputs for Text To Speech inference
kelas huggingface_hub.TextToSpeechOutput
< source >( audio: typing.Anysampling_rate: float | None = None )
Output inferensi untuk tugas Text To Speech
kelas huggingface_hub.TextToSpeechParameters
< source >( generation_parameters: huggingface_hub.inference._generated.types.text_to_speech.TextToSpeechGenerationParameters | None = None )
Parameter inferensi tambahan untuk Text To Speech
text_to_video
kelas huggingface_hub.TextToVideoInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.text_to_video.TextToVideoParameters | None = None )
Inputs for Text To Video inference
Output inferensi untuk tugas Text To Video
kelas huggingface_hub.TextToVideoParameters
< source >( guidance_scale: float | None = Nonenegative_prompt: list[str] | None = Nonenum_frames: float | None = Nonenum_inference_steps: int | None = Noneseed: int | None = None )
Parameter inferensi tambahan untuk Text To Video
token_classification
kelas huggingface_hub.TokenClassificationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.token_classification.TokenClassificationParameters | None = None )
Input untuk inferensi Token Classification
kelas huggingface_hub.TokenClassificationOutputElement
< source >( end: intscore: floatstart: intword: strentity: str | None = Noneentity_group: str | None = None )
Output inferensi untuk tugas Klasifikasi Token
kelas huggingface_hub.TokenClassificationParameters
< source >( aggregation_strategy: typing.Optional[ForwardRef('TokenClassificationAggregationStrategy')] = Noneignore_labels: list[str] | None = Nonestride: int | None = None )
Parameter inferensi tambahan untuk Klasifikasi Token
terjemahan
kelas huggingface_hub.TranslationInput
< source >( inputs: strparameters: huggingface_hub.inference._generated.types.translation.TranslationParameters | None = None )
Input untuk inferensi Translation
Hasil inferensi untuk tugas Terjemahan
kelas huggingface_hub.TranslationParameters
< source >( clean_up_tokenization_spaces: bool | None = Nonegenerate_parameters: dict[str, typing.Any] | None = Nonesrc_lang: str | None = Nonetgt_lang: str | None = Nonetruncation: typing.Optional[ForwardRef('TranslationTruncationStrategy')] = None )
Parameter inferensi tambahan untuk Translation
video_classification
kelas huggingface_hub.VideoClassificationInput
< source >( inputs: typing.Anyparameters: huggingface_hub.inference._generated.types.video_classification.VideoClassificationParameters | None = None )
Input untuk inferensi Klasifikasi Video
Output inferensi untuk tugas Klasifikasi Video
kelas huggingface_hub.VideoClassificationParameters
< source >( frame_sampling_rate: int | None = Nonefunction_to_apply: typing.Optional[ForwardRef('VideoClassificationOutputTransform')] = Nonenum_frames: int | None = Nonetop_k: int | None = None )
Parameter inferensi tambahan untuk Klasifikasi Video
visual_question_answering
kelas huggingface_hub.VisualQuestionAnsweringInput
< source >( inputs: VisualQuestionAnsweringInputDataparameters: huggingface_hub.inference._generated.types.visual_question_answering.VisualQuestionAnsweringParameters | None = None )
Input untuk inferensi Visual Question Answering
kelas huggingface_hub.VisualQuestionAnsweringInputData
< source >( image: typing.Anyquestion: str )
Satu pasangan (gambar, pertanyaan) untuk dijawab
kelas huggingface_hub.VisualQuestionAnsweringOutputElement
< source >( score: floatanswer: str | None = None )
Output inferensi untuk tugas Visual Question Answering
Parameter inferensi tambahan untuk Visual Question Answering
zero_shot_classification
kelas huggingface_hub.ZeroShotClassificationInput
< source >( inputs: strparameters: ZeroShotClassificationParameters )
Input untuk inferensi Zero Shot Classification
Output inferensi untuk tugas Klasifikasi Nol Tembakan
kelas huggingface_hub.ZeroShotClassificationParameters
< source >( candidate_labels: listhypothesis_template: str | None = Nonemulti_label: bool | None = None )
Parameter inferensi tambahan untuk Zero Shot Classification
zero_shot_image_classification
kelas huggingface_hub.ZeroShotImageClassificationInput
< source >( inputs: strparameters: ZeroShotImageClassificationParameters )
Input untuk inferensi Zero Shot Image Classification
kelas huggingface_hub.ZeroShotImageClassificationOutputElement
< source >( label: strscore: float )
Output inferensi untuk tugas Klasifikasi Gambar Zero Shot
kelas huggingface_hub.ZeroShotImageClassificationParameters
< source >( candidate_labels: listhypothesis_template: str | None = None )
Parameter inferensi tambahan untuk Zero Shot Image Classification
zero_shot_object_detection
kelas huggingface_hub.ZeroShotObjectDetectionBoundingBox
< source >( xmax: intxmin: intymax: intymin: int )
Kotak batas yang diprediksi. Koordinat relatif terhadap sudut kiri atas gambar input.
kelas huggingface_hub.ZeroShotObjectDetectionInput
< source >( inputs: strparameters: ZeroShotObjectDetectionParameters )
Input untuk inferensi Zero Shot Object Detection
kelas huggingface_hub.ZeroShotObjectDetectionOutputElement
< source >( box: ZeroShotObjectDetectionBoundingBoxlabel: strscore: float )
Hasil inferensi untuk tugas Deteksi Objek Nol Tembakan
Parameter inferensi tambahan untuk Zero Shot Object Detection