diff --git a/docs/api-inference/tasks/audio-classification.md b/docs/api-inference/tasks/audio-classification.md index f91a18dc3..8f8f80cac 100644 --- a/docs/api-inference/tasks/audio-classification.md +++ b/docs/api-inference/tasks/audio-classification.md @@ -104,7 +104,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload. | -| **parameters** | _object_ | Additional inference parameters for Audio Classification | +| **parameters** | _object_ | | | **        function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. | | **        top_k** | _integer_ | When specified, limits the output to the top K most probable classes. | diff --git a/docs/api-inference/tasks/automatic-speech-recognition.md b/docs/api-inference/tasks/automatic-speech-recognition.md index aa1926f20..15d5d0556 100644 --- a/docs/api-inference/tasks/automatic-speech-recognition.md +++ b/docs/api-inference/tasks/automatic-speech-recognition.md @@ -105,9 +105,9 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload. | -| **parameters** | _object_ | Additional inference parameters for Automatic Speech Recognition | +| **parameters** | _object_ | | | **        return_timestamps** | _boolean_ | Whether to output corresponding timestamps with the generated text | -| **        generation_parameters** | _object_ | Ad-hoc parametrization of the text generation process | +| **        generation_parameters** | _object_ | | | **                temperature** | _number_ | The value used to modulate the next token probabilities. | | **                top_k** | _integer_ | The number of highest probability vocabulary tokens to keep for top-k-filtering. | | **                top_p** | _number_ | If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation. | diff --git a/docs/api-inference/tasks/fill-mask.md b/docs/api-inference/tasks/fill-mask.md index b4c07c07a..3f1ecbd4c 100644 --- a/docs/api-inference/tasks/fill-mask.md +++ b/docs/api-inference/tasks/fill-mask.md @@ -100,7 +100,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The text with masked tokens | -| **parameters** | _object_ | Additional inference parameters for Fill Mask | +| **parameters** | _object_ | | | **        top_k** | _integer_ | When passed, overrides the number of predictions to return. | | **        targets** | _string[]_ | When passed, the model will limit the scores to the passed targets instead of looking up in the whole vocabulary. If the provided targets are not in the model vocab, they will be tokenized and the first resulting token will be used (with a warning, and that might be slower). | diff --git a/docs/api-inference/tasks/image-classification.md b/docs/api-inference/tasks/image-classification.md index 31a4e68f7..baab2aa40 100644 --- a/docs/api-inference/tasks/image-classification.md +++ b/docs/api-inference/tasks/image-classification.md @@ -99,7 +99,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload. | -| **parameters** | _object_ | Additional inference parameters for Image Classification | +| **parameters** | _object_ | | | **        function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. | | **        top_k** | _integer_ | When specified, limits the output to the top K most probable classes. | diff --git a/docs/api-inference/tasks/image-segmentation.md b/docs/api-inference/tasks/image-segmentation.md index 7163f3fd0..6918f0895 100644 --- a/docs/api-inference/tasks/image-segmentation.md +++ b/docs/api-inference/tasks/image-segmentation.md @@ -100,7 +100,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload. | -| **parameters** | _object_ | Additional inference parameters for Image Segmentation | +| **parameters** | _object_ | | | **        mask_threshold** | _number_ | Threshold to use when turning the predicted masks into binary values. | | **        overlap_mask_area_threshold** | _number_ | Mask overlap threshold to eliminate small, disconnected segments. | | **        subtask** | _enum_ | Possible values: instance, panoptic, semantic. | diff --git a/docs/api-inference/tasks/image-to-image.md b/docs/api-inference/tasks/image-to-image.md index 1c2f277b3..0d821f737 100644 --- a/docs/api-inference/tasks/image-to-image.md +++ b/docs/api-inference/tasks/image-to-image.md @@ -47,7 +47,7 @@ No snippet available for this task. | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload. | -| **parameters** | _object_ | Additional inference parameters for Image To Image | +| **parameters** | _object_ | | | **        guidance_scale** | _number_ | For diffusion models. A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. | | **        negative_prompt** | _string[]_ | One or several prompt to guide what NOT to include in image generation. | | **        num_inference_steps** | _integer_ | For diffusion models. The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. | diff --git a/docs/api-inference/tasks/object-detection.md b/docs/api-inference/tasks/object-detection.md index 40ed3f7d4..527ccc260 100644 --- a/docs/api-inference/tasks/object-detection.md +++ b/docs/api-inference/tasks/object-detection.md @@ -99,7 +99,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload. | -| **parameters** | _object_ | Additional inference parameters for Object Detection | +| **parameters** | _object_ | | | **        threshold** | _number_ | The probability necessary to make a prediction. | diff --git a/docs/api-inference/tasks/question-answering.md b/docs/api-inference/tasks/question-answering.md index c4aa92441..1bf60e26d 100644 --- a/docs/api-inference/tasks/question-answering.md +++ b/docs/api-inference/tasks/question-answering.md @@ -109,7 +109,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | **inputs*** | _object_ | One (context, question) pair to answer | | **        context*** | _string_ | The context to be used for answering the question | | **        question*** | _string_ | The question to be answered | -| **parameters** | _object_ | Additional inference parameters for Question Answering | +| **parameters** | _object_ | | | **        top_k** | _integer_ | The number of answers to return (will be chosen by order of likelihood). Note that we return less than topk answers if there are not enough options available within the context. | | **        doc_stride** | _integer_ | If the context is too long to fit with the question for the model, it will be split in several chunks with some overlap. This argument controls the size of that overlap. | | **        max_answer_len** | _integer_ | The maximum length of predicted answers (e.g., only answers with a shorter length are considered). | diff --git a/docs/api-inference/tasks/summarization.md b/docs/api-inference/tasks/summarization.md index 6a46c6d6a..4df607752 100644 --- a/docs/api-inference/tasks/summarization.md +++ b/docs/api-inference/tasks/summarization.md @@ -99,7 +99,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input text to summarize. | -| **parameters** | _object_ | Additional inference parameters for summarization. | +| **parameters** | _object_ | | | **        clean_up_tokenization_spaces** | _boolean_ | Whether to clean up the potential extra spaces in the text output. | | **        truncation** | _enum_ | Possible values: do_not_truncate, longest_first, only_first, only_second. | | **        generate_parameters** | _object_ | Additional parametrization of the text generation algorithm. | diff --git a/docs/api-inference/tasks/table-question-answering.md b/docs/api-inference/tasks/table-question-answering.md index 689e6a0b2..9f409170c 100644 --- a/docs/api-inference/tasks/table-question-answering.md +++ b/docs/api-inference/tasks/table-question-answering.md @@ -125,7 +125,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | **inputs*** | _object_ | One (table, question) pair to answer | | **        table*** | _object_ | The table to serve as context for the questions | | **        question*** | _string_ | The question to be answered about the table | -| **parameters** | _object_ | Additional inference parameters for Table Question Answering | +| **parameters** | _object_ | | Some options can be configured by passing headers to the Inference API. Here are the available headers: diff --git a/docs/api-inference/tasks/text-classification.md b/docs/api-inference/tasks/text-classification.md index 96640c5b0..f88fb3f89 100644 --- a/docs/api-inference/tasks/text-classification.md +++ b/docs/api-inference/tasks/text-classification.md @@ -103,7 +103,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The text to classify | -| **parameters** | _object_ | Additional inference parameters for Text Classification | +| **parameters** | _object_ | | | **        function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. | | **        top_k** | _integer_ | When specified, limits the output to the top K most probable classes. | diff --git a/docs/api-inference/tasks/text-to-image.md b/docs/api-inference/tasks/text-to-image.md index b454b8fb7..047851014 100644 --- a/docs/api-inference/tasks/text-to-image.md +++ b/docs/api-inference/tasks/text-to-image.md @@ -113,7 +113,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input text data (sometimes called "prompt") | -| **parameters** | _object_ | Additional inference parameters for Text To Image | +| **parameters** | _object_ | | | **        guidance_scale** | _number_ | A higher guidance scale value encourages the model to generate images closely linked to the text prompt, but values too high may cause saturation and other artifacts. | | **        negative_prompt** | _string[]_ | One or several prompt to guide what NOT to include in image generation. | | **        num_inference_steps** | _integer_ | The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. | diff --git a/docs/api-inference/tasks/token-classification.md b/docs/api-inference/tasks/token-classification.md index 3ce03dd37..8826fe1f4 100644 --- a/docs/api-inference/tasks/token-classification.md +++ b/docs/api-inference/tasks/token-classification.md @@ -102,7 +102,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The input text data | -| **parameters** | _object_ | Additional inference parameters for Token Classification | +| **parameters** | _object_ | | | **        ignore_labels** | _string[]_ | A list of labels to ignore | | **        stride** | _integer_ | The number of overlapping tokens between chunks when splitting the input text. | | **        aggregation_strategy** | _string_ | One of the following: | diff --git a/docs/api-inference/tasks/translation.md b/docs/api-inference/tasks/translation.md index 18263b71e..0a41bd31a 100644 --- a/docs/api-inference/tasks/translation.md +++ b/docs/api-inference/tasks/translation.md @@ -99,7 +99,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The text to translate. | -| **parameters** | _object_ | Additional inference parameters for Translation | +| **parameters** | _object_ | | | **        src_lang** | _string_ | The source language of the text. Required for models that can translate from multiple languages. | | **        tgt_lang** | _string_ | Target language to translate to. Required for models that can translate to multiple languages. | | **        clean_up_tokenization_spaces** | _boolean_ | Whether to clean up the potential extra spaces in the text output. | diff --git a/docs/api-inference/tasks/zero-shot-classification.md b/docs/api-inference/tasks/zero-shot-classification.md index 526b418be..5508e3912 100644 --- a/docs/api-inference/tasks/zero-shot-classification.md +++ b/docs/api-inference/tasks/zero-shot-classification.md @@ -101,7 +101,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/ | Payload | | | | :--- | :--- | :--- | | **inputs*** | _string_ | The text to classify | -| **parameters*** | _object_ | Additional inference parameters for Zero Shot Classification | +| **parameters*** | _object_ | | | **        candidate_labels*** | _string[]_ | The set of possible class labels to classify the text into. | | **        hypothesis_template** | _string_ | The sentence used in conjunction with `candidate_labels` to attempt the text classification by replacing the placeholder with the candidate labels. | | **        multi_label** | _boolean_ | Whether multiple candidate labels can be true. If false, the scores are normalized such that the sum of the label likelihoods for each sequence is 1. If true, the labels are considered independent and probabilities are normalized for each candidate. |