@huggingface/tasks 0.3.0 → 0.3.2

package/dist/index.d.ts

@@ -104,18 +104,9 @@ declare const PIPELINE_DATA: {
         modality: "nlp";
         color: "indigo";
     };
-    conversational: {
-        name: string;
-        subtasks: {
-            type: string;
-            name: string;
-        }[];
-        modality: "nlp";
-        color: "green";
-    };
     "feature-extraction": {
         name: string;
-        modality: "multimodal";
+        modality: "nlp";
         color: "red";
     };
     "text-generation": {
@@ -218,7 +209,7 @@ declare const PIPELINE_DATA: {
     };
     "text-to-image": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "yellow";
     };
     "image-to-text": {
@@ -227,7 +218,7 @@ declare const PIPELINE_DATA: {
             type: string;
             name: string;
         }[];
-        modality: "multimodal";
+        modality: "cv";
         color: "red";
     };
     "image-to-image": {
@@ -241,7 +232,7 @@ declare const PIPELINE_DATA: {
     };
     "image-to-video": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "indigo";
     };
     "unconditional-image-generation": {
@@ -334,9 +325,15 @@ declare const PIPELINE_DATA: {
     };
     "text-to-video": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "green";
     };
+    "image-text-to-text": {
+        name: string;
+        modality: "multimodal";
+        color: "red";
+        hideInDatasets: true;
+    };
     "visual-question-answering": {
         name: string;
         subtasks: {
@@ -363,7 +360,7 @@ declare const PIPELINE_DATA: {
     };
     "graph-ml": {
         name: string;
-        modality: "multimodal";
+        modality: "other";
         color: "green";
     };
     "mask-generation": {
@@ -378,14 +375,19 @@ declare const PIPELINE_DATA: {
     };
     "text-to-3d": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "yellow";
     };
     "image-to-3d": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "green";
     };
+    "image-feature-extraction": {
+        name: string;
+        modality: "cv";
+        color: "indigo";
+    };
     other: {
         name: string;
         modality: "other";
@@ -395,9 +397,10 @@ declare const PIPELINE_DATA: {
     };
 };
 type PipelineType = keyof typeof PIPELINE_DATA;
-declare const PIPELINE_TYPES: ("other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "conversational" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d")[];
+type WidgetType = PipelineType | "conversational";
+declare const PIPELINE_TYPES: ("other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d" | "image-feature-extraction")[];
 declare const SUBTASK_TYPES: string[];
-declare const PIPELINE_TYPES_SET: Set<"other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "conversational" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d">;
+declare const PIPELINE_TYPES_SET: Set<"other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d" | "image-feature-extraction">;
 
 /**
  * See default-widget-inputs.ts for the default widget inputs, this files only contains the types
@@ -477,6 +480,21 @@ type WidgetExample<TOutput = WidgetExampleOutput> = WidgetExampleTextInput<TOutp
 type KeysOfUnion<T> = T extends unknown ? keyof T : never;
 type WidgetExampleAttribute = KeysOfUnion<WidgetExample>;
 
+declare const SPECIAL_TOKENS_ATTRIBUTES: readonly ["bos_token", "eos_token", "unk_token", "sep_token", "pad_token", "cls_token", "mask_token"];
+/**
+ * Public interface for a tokenizer's special tokens mapping
+ */
+type SpecialTokensMap = {
+    [key in (typeof SPECIAL_TOKENS_ATTRIBUTES)[number]]?: string;
+};
+/**
+ * Public interface for tokenizer config
+ */
+interface TokenizerConfig extends SpecialTokensMap {
+    use_default_system_prompt?: boolean;
+    chat_template?: string;
+}
+
 declare enum InferenceDisplayability {
     /**
      * Yes
@@ -531,6 +549,7 @@ interface ModelData {
             base_model_name?: string;
             task_type?: string;
         };
+        tokenizer?: TokenizerConfig;
     };
     /**
      * all the model tags
@@ -1044,7 +1063,7 @@ declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("sklearn" | "adapter-transformers
  */
 declare const LIBRARY_TASK_MAPPING_EXCLUDING_TRANSFORMERS: Partial<Record<ModelLibraryKey, PipelineType[]>>;
 
-type PerLanguageMapping = Map<PipelineType, string[] | WidgetExample[]>;
+type PerLanguageMapping = Map<WidgetType, string[] | WidgetExample[]>;
 declare const MAPPING_DEFAULT_WIDGET: Map<string, PerLanguageMapping>;
 
 /**
@@ -1212,4 +1231,4 @@ declare namespace index {
   };
 }
 
-export { ALL_DISPLAY_MODEL_LIBRARY_KEYS, ALL_MODEL_LIBRARY_KEYS, ExampleRepo, InferenceDisplayability, LIBRARY_TASK_MAPPING_EXCLUDING_TRANSFORMERS, LibraryUiElement, MAPPING_DEFAULT_WIDGET, MODALITIES, MODALITY_LABELS, MODEL_LIBRARIES_UI_ELEMENTS, Modality, ModelData, ModelLibraryKey, PIPELINE_DATA, PIPELINE_TYPES, PIPELINE_TYPES_SET, PipelineData, PipelineType, SUBTASK_TYPES, TASKS_DATA, TASKS_MODEL_LIBRARIES, TaskData, TaskDataCustom, TaskDemo, TaskDemoEntry, TransformersInfo, WidgetExample, WidgetExampleAssetAndPromptInput, WidgetExampleAssetAndTextInput, WidgetExampleAssetAndZeroShotInput, WidgetExampleAssetInput, WidgetExampleAttribute, WidgetExampleOutput, WidgetExampleOutputAnswerScore, WidgetExampleOutputLabels, WidgetExampleOutputText, WidgetExampleOutputUrl, WidgetExampleSentenceSimilarityInput, WidgetExampleStructuredDataInput, WidgetExampleTableDataInput, WidgetExampleTextAndContextInput, WidgetExampleTextAndTableInput, WidgetExampleTextInput, WidgetExampleZeroShotTextInput, index as snippets };
+export { ALL_DISPLAY_MODEL_LIBRARY_KEYS, ALL_MODEL_LIBRARY_KEYS, ExampleRepo, InferenceDisplayability, LIBRARY_TASK_MAPPING_EXCLUDING_TRANSFORMERS, LibraryUiElement, MAPPING_DEFAULT_WIDGET, MODALITIES, MODALITY_LABELS, MODEL_LIBRARIES_UI_ELEMENTS, Modality, ModelData, ModelLibraryKey, PIPELINE_DATA, PIPELINE_TYPES, PIPELINE_TYPES_SET, PipelineData, PipelineType, SPECIAL_TOKENS_ATTRIBUTES, SUBTASK_TYPES, SpecialTokensMap, TASKS_DATA, TASKS_MODEL_LIBRARIES, TaskData, TaskDataCustom, TaskDemo, TaskDemoEntry, TokenizerConfig, TransformersInfo, WidgetExample, WidgetExampleAssetAndPromptInput, WidgetExampleAssetAndTextInput, WidgetExampleAssetAndZeroShotInput, WidgetExampleAssetInput, WidgetExampleAttribute, WidgetExampleOutput, WidgetExampleOutputAnswerScore, WidgetExampleOutputLabels, WidgetExampleOutputText, WidgetExampleOutputUrl, WidgetExampleSentenceSimilarityInput, WidgetExampleStructuredDataInput, WidgetExampleTableDataInput, WidgetExampleTextAndContextInput, WidgetExampleTextAndTableInput, WidgetExampleTextInput, WidgetExampleZeroShotTextInput, WidgetType, index as snippets };