@huggingface/tasks 0.0.7 → 0.0.8

package/dist/index.d.ts

@@ -276,6 +276,10 @@ declare const PIPELINE_DATA: {
     };
     "image-to-image": {
         name: string;
+        subtasks: {
+            type: string;
+            name: string;
+        }[];
         modality: "cv";
         color: "indigo";
     };
@@ -416,6 +420,16 @@ declare const PIPELINE_DATA: {
         modality: "cv";
         color: "yellow";
     };
+    "text-to-3d": {
+        name: string;
+        modality: "multimodal";
+        color: "yellow";
+    };
+    "image-to-3d": {
+        name: string;
+        modality: "multimodal";
+        color: "green";
+    };
     other: {
         name: string;
         modality: "other";
@@ -425,9 +439,9 @@ 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")[];
+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")[];
 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">;
+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">;
 
 /**
  * Mapping from library name (excluding Transformers) to its supported tasks.
@@ -758,10 +772,13 @@ declare namespace curl {
 }
 
 declare const snippetZeroShotClassification$1: (model: ModelData) => string;
+declare const snippetZeroShotImageClassification: (model: ModelData) => string;
 declare const snippetBasic$1: (model: ModelData) => string;
 declare const snippetFile$1: (model: ModelData) => string;
 declare const snippetTextToImage$1: (model: ModelData) => string;
+declare const snippetTabular: (model: ModelData) => string;
 declare const snippetTextToAudio$1: (model: ModelData) => string;
+declare const snippetDocumentQuestionAnswering: (model: ModelData) => string;
 declare const pythonSnippets: Partial<Record<PipelineType, (model: ModelData) => string>>;
 declare function getPythonInferenceSnippet(model: ModelData, accessToken: string): string;
 declare function hasPythonInferenceSnippet(model: ModelData): boolean;
@@ -769,16 +786,22 @@ declare function hasPythonInferenceSnippet(model: ModelData): boolean;
 declare const python_getPythonInferenceSnippet: typeof getPythonInferenceSnippet;
 declare const python_hasPythonInferenceSnippet: typeof hasPythonInferenceSnippet;
 declare const python_pythonSnippets: typeof pythonSnippets;
+declare const python_snippetDocumentQuestionAnswering: typeof snippetDocumentQuestionAnswering;
+declare const python_snippetTabular: typeof snippetTabular;
+declare const python_snippetZeroShotImageClassification: typeof snippetZeroShotImageClassification;
 declare namespace python {
   export {
     python_getPythonInferenceSnippet as getPythonInferenceSnippet,
     python_hasPythonInferenceSnippet as hasPythonInferenceSnippet,
     python_pythonSnippets as pythonSnippets,
     snippetBasic$1 as snippetBasic,
+    python_snippetDocumentQuestionAnswering as snippetDocumentQuestionAnswering,
     snippetFile$1 as snippetFile,
+    python_snippetTabular as snippetTabular,
     snippetTextToAudio$1 as snippetTextToAudio,
     snippetTextToImage$1 as snippetTextToImage,
     snippetZeroShotClassification$1 as snippetZeroShotClassification,
+    python_snippetZeroShotImageClassification as snippetZeroShotImageClassification,
   };
 }
 

package/dist/index.js

@@ -1801,6 +1801,20 @@ var PIPELINE_DATA = {
   },
   "image-to-image": {
     name: "Image-to-Image",
+    subtasks: [
+      {
+        type: "image-inpainting",
+        name: "Image Inpainting"
+      },
+      {
+        type: "image-colorization",
+        name: "Image Colorization"
+      },
+      {
+        type: "super-resolution",
+        name: "Super Resolution"
+      }
+    ],
     modality: "cv",
     color: "indigo"
   },
@@ -1987,6 +2001,16 @@ var PIPELINE_DATA = {
     modality: "cv",
     color: "yellow"
   },
+  "text-to-3d": {
+    name: "Text-to-3D",
+    modality: "multimodal",
+    color: "yellow"
+  },
+  "image-to-3d": {
+    name: "Image-to-3D",
+    modality: "multimodal",
+    color: "green"
+  },
   other: {
     name: "Other",
     modality: "other",
@@ -4406,18 +4430,18 @@ var data_default33 = taskData33;
 
 // src/tasks/index.ts
 var TASKS_MODEL_LIBRARIES = {
-  "audio-classification": ["speechbrain", "transformers"],
+  "audio-classification": ["speechbrain", "transformers", "transformers.js"],
   "audio-to-audio": ["asteroid", "speechbrain"],
   "automatic-speech-recognition": ["espnet", "nemo", "speechbrain", "transformers", "transformers.js"],
   conversational: ["transformers"],
-  "depth-estimation": ["transformers"],
-  "document-question-answering": ["transformers"],
+  "depth-estimation": ["transformers", "transformers.js"],
+  "document-question-answering": ["transformers", "transformers.js"],
   "feature-extraction": ["sentence-transformers", "transformers", "transformers.js"],
   "fill-mask": ["transformers", "transformers.js"],
   "graph-ml": ["transformers"],
   "image-classification": ["keras", "timm", "transformers", "transformers.js"],
   "image-segmentation": ["transformers", "transformers.js"],
-  "image-to-image": ["diffusers"],
+  "image-to-image": ["diffusers", "transformers.js"],
   "image-to-text": ["transformers.js"],
   "image-to-video": ["diffusers"],
   "video-classification": ["transformers"],
@@ -4439,8 +4463,8 @@ var TASKS_MODEL_LIBRARIES = {
   "text-generation": ["transformers", "transformers.js"],
   "text-retrieval": [],
   "text-to-image": ["diffusers"],
-  "text-to-speech": ["espnet", "tensorflowtts", "transformers"],
-  "text-to-audio": ["transformers"],
+  "text-to-speech": ["espnet", "tensorflowtts", "transformers", "transformers.js"],
+  "text-to-audio": ["transformers", "transformers.js"],
   "text-to-video": ["diffusers"],
   "text2text-generation": ["transformers", "transformers.js"],
   "time-series-forecasting": [],
@@ -4455,11 +4479,13 @@ var TASKS_MODEL_LIBRARIES = {
   ],
   translation: ["transformers", "transformers.js"],
   "unconditional-image-generation": ["diffusers"],
-  "visual-question-answering": ["transformers"],
+  "visual-question-answering": ["transformers", "transformers.js"],
   "voice-activity-detection": [],
   "zero-shot-classification": ["transformers", "transformers.js"],
   "zero-shot-image-classification": ["transformers", "transformers.js"],
-  "zero-shot-object-detection": ["transformers"]
+  "zero-shot-object-detection": ["transformers", "transformers.js"],
+  "text-to-3d": [],
+  "image-to-3d": []
 };
 function getData(type, partialTaskData = data_default14) {
   return {
@@ -4515,7 +4541,9 @@ var TASKS_DATA = {
   "voice-activity-detection": void 0,
   "zero-shot-classification": getData("zero-shot-classification", data_default32),
   "zero-shot-image-classification": getData("zero-shot-image-classification", data_default33),
-  "zero-shot-object-detection": getData("zero-shot-object-detection", data_default14)
+  "zero-shot-object-detection": getData("zero-shot-object-detection", data_default14),
+  "text-to-3d": getData("text-to-3d", data_default14),
+  "image-to-3d": getData("image-to-3d", data_default14)
 };
 
 // src/model-libraries.ts
@@ -4622,6 +4650,10 @@ var inputsTableQuestionAnswering = () => `{
 			]
 		}
 	}`;
+var inputsVisualQuestionAnswering = () => `{
+		"image": "cat.png",
+		"question": "What is in this image?"
+	}`;
 var inputsQuestionAnswering = () => `{
 		"question": "What is my name?",
 		"context": "My name is Clara and I live in Berkeley."
@@ -4650,11 +4682,14 @@ var inputsTextToImage = () => `"Astronaut riding a horse"`;
 var inputsTextToSpeech = () => `"The answer to the universe is 42"`;
 var inputsTextToAudio = () => `"liquid drum and bass, atmospheric synths, airy sounds"`;
 var inputsAutomaticSpeechRecognition = () => `"sample1.flac"`;
+var inputsTabularPrediction = () => `'{"Height":[11.52,12.48],"Length1":[23.2,24.0],"Length2":[25.4,26.3],"Species": ["Bream","Bream"]}'`;
+var inputsZeroShotImageClassification = () => `"cats.jpg"`;
 var modelInputSnippets = {
   "audio-to-audio": inputsAudioToAudio,
   "audio-classification": inputsAudioClassification,
   "automatic-speech-recognition": inputsAutomaticSpeechRecognition,
   conversational: inputsConversational,
+  "document-question-answering": inputsVisualQuestionAnswering,
   "feature-extraction": inputsFeatureExtraction,
   "fill-mask": inputsFillMask,
   "image-classification": inputsImageClassification,
@@ -4665,6 +4700,8 @@ var modelInputSnippets = {
   "sentence-similarity": inputsSentenceSimilarity,
   summarization: inputsSummarization,
   "table-question-answering": inputsTableQuestionAnswering,
+  "tabular-regression": inputsTabularPrediction,
+  "tabular-classification": inputsTabularPrediction,
   "text-classification": inputsTextClassification,
   "text-generation": inputsTextGeneration,
   "text-to-image": inputsTextToImage,
@@ -4673,7 +4710,8 @@ var modelInputSnippets = {
   "text2text-generation": inputsText2TextGeneration,
   "token-classification": inputsTokenClassification,
   translation: inputsTranslation,
-  "zero-shot-classification": inputsZeroShotClassification
+  "zero-shot-classification": inputsZeroShotClassification,
+  "zero-shot-image-classification": inputsZeroShotImageClassification
 };
 function getModelInputSnippet(model, noWrap = false, noQuotes = false) {
   if (model.pipeline_tag) {
@@ -4761,10 +4799,13 @@ __export(python_exports, {
   hasPythonInferenceSnippet: () => hasPythonInferenceSnippet,
   pythonSnippets: () => pythonSnippets,
   snippetBasic: () => snippetBasic2,
+  snippetDocumentQuestionAnswering: () => snippetDocumentQuestionAnswering,
   snippetFile: () => snippetFile2,
+  snippetTabular: () => snippetTabular,
   snippetTextToAudio: () => snippetTextToAudio,
   snippetTextToImage: () => snippetTextToImage,
-  snippetZeroShotClassification: () => snippetZeroShotClassification2
+  snippetZeroShotClassification: () => snippetZeroShotClassification2,
+  snippetZeroShotImageClassification: () => snippetZeroShotImageClassification
 });
 var snippetZeroShotClassification2 = (model) => `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
@@ -4774,6 +4815,20 @@ output = query({
     "inputs": ${getModelInputSnippet(model)},
     "parameters": {"candidate_labels": ["refund", "legal", "faq"]},
 })`;
+var snippetZeroShotImageClassification = (model) => `def query(data):
+	with open(data["image_path"], "rb") as f:
+		img = f.read()
+	payload={
+		"parameters": data["parameters"],
+		"inputs": base64.b64encode(img).decode("utf-8")
+	}
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+output = query({
+    "image_path": ${getModelInputSnippet(model)},
+    "parameters": {"candidate_labels": ["cat", "dog", "llama"]},
+})`;
 var snippetBasic2 = (model) => `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
 	return response.json()
@@ -4798,6 +4853,12 @@ image_bytes = query({
 import io
 from PIL import Image
 image = Image.open(io.BytesIO(image_bytes))`;
+var snippetTabular = (model) => `def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.content
+response = query({
+	"inputs": {"data": ${getModelInputSnippet(model)}},
+})`;
 var snippetTextToAudio = (model) => {
   if (model.library_name === "transformers") {
     return `def query(payload):
@@ -4823,8 +4884,18 @@ from IPython.display import Audio
 Audio(audio, rate=sampling_rate)`;
   }
 };
+var snippetDocumentQuestionAnswering = (model) => `def query(payload):
+ 	with open(payload["image"], "rb") as f:
+  		img = f.read()
+		payload["image"] = base64.b64encode(img).decode("utf-8")  
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+output = query({
+    "inputs": ${getModelInputSnippet(model)},
+})`;
 var pythonSnippets = {
-  // Same order as in js/src/lib/interfaces/Types.ts
+  // Same order as in tasks/src/pipelines.ts
   "text-classification": snippetBasic2,
   "token-classification": snippetBasic2,
   "table-question-answering": snippetBasic2,
@@ -4845,9 +4916,13 @@ var pythonSnippets = {
   "audio-to-audio": snippetFile2,
   "audio-classification": snippetFile2,
   "image-classification": snippetFile2,
-  "image-to-text": snippetFile2,
+  "tabular-regression": snippetTabular,
+  "tabular-classification": snippetTabular,
   "object-detection": snippetFile2,
-  "image-segmentation": snippetFile2
+  "image-segmentation": snippetFile2,
+  "document-question-answering": snippetDocumentQuestionAnswering,
+  "image-to-text": snippetFile2,
+  "zero-shot-image-classification": snippetZeroShotImageClassification
 };
 function getPythonInferenceSnippet(model, accessToken) {
   const body = model.pipeline_tag && model.pipeline_tag in pythonSnippets ? pythonSnippets[model.pipeline_tag]?.(model) ?? "" : "";

package/dist/index.mjs

@@ -1763,6 +1763,20 @@ var PIPELINE_DATA = {
   },
   "image-to-image": {
     name: "Image-to-Image",
+    subtasks: [
+      {
+        type: "image-inpainting",
+        name: "Image Inpainting"
+      },
+      {
+        type: "image-colorization",
+        name: "Image Colorization"
+      },
+      {
+        type: "super-resolution",
+        name: "Super Resolution"
+      }
+    ],
     modality: "cv",
     color: "indigo"
   },
@@ -1949,6 +1963,16 @@ var PIPELINE_DATA = {
     modality: "cv",
     color: "yellow"
   },
+  "text-to-3d": {
+    name: "Text-to-3D",
+    modality: "multimodal",
+    color: "yellow"
+  },
+  "image-to-3d": {
+    name: "Image-to-3D",
+    modality: "multimodal",
+    color: "green"
+  },
   other: {
     name: "Other",
     modality: "other",
@@ -4368,18 +4392,18 @@ var data_default33 = taskData33;
 
 // src/tasks/index.ts
 var TASKS_MODEL_LIBRARIES = {
-  "audio-classification": ["speechbrain", "transformers"],
+  "audio-classification": ["speechbrain", "transformers", "transformers.js"],
   "audio-to-audio": ["asteroid", "speechbrain"],
   "automatic-speech-recognition": ["espnet", "nemo", "speechbrain", "transformers", "transformers.js"],
   conversational: ["transformers"],
-  "depth-estimation": ["transformers"],
-  "document-question-answering": ["transformers"],
+  "depth-estimation": ["transformers", "transformers.js"],
+  "document-question-answering": ["transformers", "transformers.js"],
   "feature-extraction": ["sentence-transformers", "transformers", "transformers.js"],
   "fill-mask": ["transformers", "transformers.js"],
   "graph-ml": ["transformers"],
   "image-classification": ["keras", "timm", "transformers", "transformers.js"],
   "image-segmentation": ["transformers", "transformers.js"],
-  "image-to-image": ["diffusers"],
+  "image-to-image": ["diffusers", "transformers.js"],
   "image-to-text": ["transformers.js"],
   "image-to-video": ["diffusers"],
   "video-classification": ["transformers"],
@@ -4401,8 +4425,8 @@ var TASKS_MODEL_LIBRARIES = {
   "text-generation": ["transformers", "transformers.js"],
   "text-retrieval": [],
   "text-to-image": ["diffusers"],
-  "text-to-speech": ["espnet", "tensorflowtts", "transformers"],
-  "text-to-audio": ["transformers"],
+  "text-to-speech": ["espnet", "tensorflowtts", "transformers", "transformers.js"],
+  "text-to-audio": ["transformers", "transformers.js"],
   "text-to-video": ["diffusers"],
   "text2text-generation": ["transformers", "transformers.js"],
   "time-series-forecasting": [],
@@ -4417,11 +4441,13 @@ var TASKS_MODEL_LIBRARIES = {
   ],
   translation: ["transformers", "transformers.js"],
   "unconditional-image-generation": ["diffusers"],
-  "visual-question-answering": ["transformers"],
+  "visual-question-answering": ["transformers", "transformers.js"],
   "voice-activity-detection": [],
   "zero-shot-classification": ["transformers", "transformers.js"],
   "zero-shot-image-classification": ["transformers", "transformers.js"],
-  "zero-shot-object-detection": ["transformers"]
+  "zero-shot-object-detection": ["transformers", "transformers.js"],
+  "text-to-3d": [],
+  "image-to-3d": []
 };
 function getData(type, partialTaskData = data_default14) {
   return {
@@ -4477,7 +4503,9 @@ var TASKS_DATA = {
   "voice-activity-detection": void 0,
   "zero-shot-classification": getData("zero-shot-classification", data_default32),
   "zero-shot-image-classification": getData("zero-shot-image-classification", data_default33),
-  "zero-shot-object-detection": getData("zero-shot-object-detection", data_default14)
+  "zero-shot-object-detection": getData("zero-shot-object-detection", data_default14),
+  "text-to-3d": getData("text-to-3d", data_default14),
+  "image-to-3d": getData("image-to-3d", data_default14)
 };
 
 // src/model-libraries.ts
@@ -4584,6 +4612,10 @@ var inputsTableQuestionAnswering = () => `{
 			]
 		}
 	}`;
+var inputsVisualQuestionAnswering = () => `{
+		"image": "cat.png",
+		"question": "What is in this image?"
+	}`;
 var inputsQuestionAnswering = () => `{
 		"question": "What is my name?",
 		"context": "My name is Clara and I live in Berkeley."
@@ -4612,11 +4644,14 @@ var inputsTextToImage = () => `"Astronaut riding a horse"`;
 var inputsTextToSpeech = () => `"The answer to the universe is 42"`;
 var inputsTextToAudio = () => `"liquid drum and bass, atmospheric synths, airy sounds"`;
 var inputsAutomaticSpeechRecognition = () => `"sample1.flac"`;
+var inputsTabularPrediction = () => `'{"Height":[11.52,12.48],"Length1":[23.2,24.0],"Length2":[25.4,26.3],"Species": ["Bream","Bream"]}'`;
+var inputsZeroShotImageClassification = () => `"cats.jpg"`;
 var modelInputSnippets = {
   "audio-to-audio": inputsAudioToAudio,
   "audio-classification": inputsAudioClassification,
   "automatic-speech-recognition": inputsAutomaticSpeechRecognition,
   conversational: inputsConversational,
+  "document-question-answering": inputsVisualQuestionAnswering,
   "feature-extraction": inputsFeatureExtraction,
   "fill-mask": inputsFillMask,
   "image-classification": inputsImageClassification,
@@ -4627,6 +4662,8 @@ var modelInputSnippets = {
   "sentence-similarity": inputsSentenceSimilarity,
   summarization: inputsSummarization,
   "table-question-answering": inputsTableQuestionAnswering,
+  "tabular-regression": inputsTabularPrediction,
+  "tabular-classification": inputsTabularPrediction,
   "text-classification": inputsTextClassification,
   "text-generation": inputsTextGeneration,
   "text-to-image": inputsTextToImage,
@@ -4635,7 +4672,8 @@ var modelInputSnippets = {
   "text2text-generation": inputsText2TextGeneration,
   "token-classification": inputsTokenClassification,
   translation: inputsTranslation,
-  "zero-shot-classification": inputsZeroShotClassification
+  "zero-shot-classification": inputsZeroShotClassification,
+  "zero-shot-image-classification": inputsZeroShotImageClassification
 };
 function getModelInputSnippet(model, noWrap = false, noQuotes = false) {
   if (model.pipeline_tag) {
@@ -4723,10 +4761,13 @@ __export(python_exports, {
   hasPythonInferenceSnippet: () => hasPythonInferenceSnippet,
   pythonSnippets: () => pythonSnippets,
   snippetBasic: () => snippetBasic2,
+  snippetDocumentQuestionAnswering: () => snippetDocumentQuestionAnswering,
   snippetFile: () => snippetFile2,
+  snippetTabular: () => snippetTabular,
   snippetTextToAudio: () => snippetTextToAudio,
   snippetTextToImage: () => snippetTextToImage,
-  snippetZeroShotClassification: () => snippetZeroShotClassification2
+  snippetZeroShotClassification: () => snippetZeroShotClassification2,
+  snippetZeroShotImageClassification: () => snippetZeroShotImageClassification
 });
 var snippetZeroShotClassification2 = (model) => `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
@@ -4736,6 +4777,20 @@ output = query({
     "inputs": ${getModelInputSnippet(model)},
     "parameters": {"candidate_labels": ["refund", "legal", "faq"]},
 })`;
+var snippetZeroShotImageClassification = (model) => `def query(data):
+	with open(data["image_path"], "rb") as f:
+		img = f.read()
+	payload={
+		"parameters": data["parameters"],
+		"inputs": base64.b64encode(img).decode("utf-8")
+	}
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+output = query({
+    "image_path": ${getModelInputSnippet(model)},
+    "parameters": {"candidate_labels": ["cat", "dog", "llama"]},
+})`;
 var snippetBasic2 = (model) => `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
 	return response.json()
@@ -4760,6 +4815,12 @@ image_bytes = query({
 import io
 from PIL import Image
 image = Image.open(io.BytesIO(image_bytes))`;
+var snippetTabular = (model) => `def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.content
+response = query({
+	"inputs": {"data": ${getModelInputSnippet(model)}},
+})`;
 var snippetTextToAudio = (model) => {
   if (model.library_name === "transformers") {
     return `def query(payload):
@@ -4785,8 +4846,18 @@ from IPython.display import Audio
 Audio(audio, rate=sampling_rate)`;
   }
 };
+var snippetDocumentQuestionAnswering = (model) => `def query(payload):
+ 	with open(payload["image"], "rb") as f:
+  		img = f.read()
+		payload["image"] = base64.b64encode(img).decode("utf-8")  
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+output = query({
+    "inputs": ${getModelInputSnippet(model)},
+})`;
 var pythonSnippets = {
-  // Same order as in js/src/lib/interfaces/Types.ts
+  // Same order as in tasks/src/pipelines.ts
   "text-classification": snippetBasic2,
   "token-classification": snippetBasic2,
   "table-question-answering": snippetBasic2,
@@ -4807,9 +4878,13 @@ var pythonSnippets = {
   "audio-to-audio": snippetFile2,
   "audio-classification": snippetFile2,
   "image-classification": snippetFile2,
-  "image-to-text": snippetFile2,
+  "tabular-regression": snippetTabular,
+  "tabular-classification": snippetTabular,
   "object-detection": snippetFile2,
-  "image-segmentation": snippetFile2
+  "image-segmentation": snippetFile2,
+  "document-question-answering": snippetDocumentQuestionAnswering,
+  "image-to-text": snippetFile2,
+  "zero-shot-image-classification": snippetZeroShotImageClassification
 };
 function getPythonInferenceSnippet(model, accessToken) {
   const body = model.pipeline_tag && model.pipeline_tag in pythonSnippets ? pythonSnippets[model.pipeline_tag]?.(model) ?? "" : "";

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.0.7",
+  "version": "0.0.8",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {
@@ -30,9 +30,7 @@
   ],
   "author": "Hugging Face",
   "license": "MIT",
-  "devDependencies": {
-    "typescript": "^5.0.4"
-  },
+  "devDependencies": {},
   "scripts": {
     "lint": "eslint --quiet --fix --ext .cjs,.ts .",
     "lint:check": "eslint --ext .cjs,.ts .",

package/src/pipelines.ts

@@ -435,6 +435,20 @@ export const PIPELINE_DATA = {
 	},
 	"image-to-image": {
 		name: "Image-to-Image",
+		subtasks: [
+			{
+				type: "image-inpainting",
+				name: "Image Inpainting",
+			},
+			{
+				type: "image-colorization",
+				name: "Image Colorization",
+			},
+			{
+				type: "super-resolution",
+				name: "Super Resolution",
+			},
+		],
 		modality: "cv",
 		color: "indigo",
 	},
@@ -621,6 +635,16 @@ export const PIPELINE_DATA = {
 		modality: "cv",
 		color: "yellow",
 	},
+	"text-to-3d": {
+		name: "Text-to-3D",
+		modality: "multimodal",
+		color: "yellow",
+	},
+	"image-to-3d": {
+		name: "Image-to-3D",
+		modality: "multimodal",
+		color: "green",
+	},
 	other: {
 		name: "Other",
 		modality: "other",

package/src/snippets/inputs.ts

@@ -31,6 +31,12 @@ const inputsTableQuestionAnswering = () =>
 		}
 	}`;
 
+const inputsVisualQuestionAnswering = () =>
+	`{
+		"image": "cat.png",
+		"question": "What is in this image?"
+	}`;
+
 const inputsQuestionAnswering = () =>
 	`{
 		"question": "What is my name?",
@@ -79,6 +85,11 @@ const inputsTextToAudio = () => `"liquid drum and bass, atmospheric synths, airy
 
 const inputsAutomaticSpeechRecognition = () => `"sample1.flac"`;
 
+const inputsTabularPrediction = () =>
+	`'{"Height":[11.52,12.48],"Length1":[23.2,24.0],"Length2":[25.4,26.3],"Species": ["Bream","Bream"]}'`;
+
+const inputsZeroShotImageClassification = () => `"cats.jpg"`;
+
 const modelInputSnippets: {
 	[key in PipelineType]?: (model: ModelData) => string;
 } = {
@@ -86,6 +97,7 @@ const modelInputSnippets: {
 	"audio-classification": inputsAudioClassification,
 	"automatic-speech-recognition": inputsAutomaticSpeechRecognition,
 	conversational: inputsConversational,
+	"document-question-answering": inputsVisualQuestionAnswering,
 	"feature-extraction": inputsFeatureExtraction,
 	"fill-mask": inputsFillMask,
 	"image-classification": inputsImageClassification,
@@ -96,6 +108,8 @@ const modelInputSnippets: {
 	"sentence-similarity": inputsSentenceSimilarity,
 	summarization: inputsSummarization,
 	"table-question-answering": inputsTableQuestionAnswering,
+	"tabular-regression": inputsTabularPrediction,
+	"tabular-classification": inputsTabularPrediction,
 	"text-classification": inputsTextClassification,
 	"text-generation": inputsTextGeneration,
 	"text-to-image": inputsTextToImage,
@@ -105,6 +119,7 @@ const modelInputSnippets: {
 	"token-classification": inputsTokenClassification,
 	translation: inputsTranslation,
 	"zero-shot-classification": inputsZeroShotClassification,
+	"zero-shot-image-classification": inputsZeroShotImageClassification,
 };
 
 // Use noWrap to put the whole snippet on a single line (removing new lines and tabulations)

package/src/snippets/python.ts

@@ -12,6 +12,22 @@ output = query({
     "parameters": {"candidate_labels": ["refund", "legal", "faq"]},
 })`;
 
+export const snippetZeroShotImageClassification = (model: ModelData): string =>
+	`def query(data):
+	with open(data["image_path"], "rb") as f:
+		img = f.read()
+	payload={
+		"parameters": data["parameters"],
+		"inputs": base64.b64encode(img).decode("utf-8")
+	}
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+output = query({
+    "image_path": ${getModelInputSnippet(model)},
+    "parameters": {"candidate_labels": ["cat", "dog", "llama"]},
+})`;
+
 export const snippetBasic = (model: ModelData): string =>
 	`def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
@@ -42,6 +58,14 @@ import io
 from PIL import Image
 image = Image.open(io.BytesIO(image_bytes))`;
 
+export const snippetTabular = (model: ModelData): string =>
+	`def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.content
+response = query({
+	"inputs": {"data": ${getModelInputSnippet(model)}},
+})`;
+
 export const snippetTextToAudio = (model: ModelData): string => {
 	// Transformers TTS pipeline and api-inference-community (AIC) pipeline outputs are diverged
 	// with the latest update to inference-api (IA).
@@ -70,8 +94,21 @@ from IPython.display import Audio
 Audio(audio, rate=sampling_rate)`;
 	}
 };
+
+export const snippetDocumentQuestionAnswering = (model: ModelData): string =>
+	`def query(payload):
+ 	with open(payload["image"], "rb") as f:
+  		img = f.read()
+		payload["image"] = base64.b64encode(img).decode("utf-8")  
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+output = query({
+    "inputs": ${getModelInputSnippet(model)},
+})`;
+
 export const pythonSnippets: Partial<Record<PipelineType, (model: ModelData) => string>> = {
-	// Same order as in js/src/lib/interfaces/Types.ts
+	// Same order as in tasks/src/pipelines.ts
 	"text-classification": snippetBasic,
 	"token-classification": snippetBasic,
 	"table-question-answering": snippetBasic,
@@ -92,9 +129,13 @@ export const pythonSnippets: Partial<Record<PipelineType, (model: ModelData) =>
 	"audio-to-audio": snippetFile,
 	"audio-classification": snippetFile,
 	"image-classification": snippetFile,
-	"image-to-text": snippetFile,
+	"tabular-regression": snippetTabular,
+	"tabular-classification": snippetTabular,
 	"object-detection": snippetFile,
 	"image-segmentation": snippetFile,
+	"document-question-answering": snippetDocumentQuestionAnswering,
+	"image-to-text": snippetFile,
+	"zero-shot-image-classification": snippetZeroShotImageClassification,
 };
 
 export function getPythonInferenceSnippet(model: ModelData, accessToken: string): string {

package/src/tasks/index.ts

@@ -40,18 +40,18 @@ import type { ModelLibraryKey } from "../model-libraries";
  * Model libraries compatible with each ML task
  */
 export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
-	"audio-classification": ["speechbrain", "transformers"],
+	"audio-classification": ["speechbrain", "transformers", "transformers.js"],
 	"audio-to-audio": ["asteroid", "speechbrain"],
 	"automatic-speech-recognition": ["espnet", "nemo", "speechbrain", "transformers", "transformers.js"],
 	conversational: ["transformers"],
-	"depth-estimation": ["transformers"],
-	"document-question-answering": ["transformers"],
+	"depth-estimation": ["transformers", "transformers.js"],
+	"document-question-answering": ["transformers", "transformers.js"],
 	"feature-extraction": ["sentence-transformers", "transformers", "transformers.js"],
 	"fill-mask": ["transformers", "transformers.js"],
 	"graph-ml": ["transformers"],
 	"image-classification": ["keras", "timm", "transformers", "transformers.js"],
 	"image-segmentation": ["transformers", "transformers.js"],
-	"image-to-image": ["diffusers"],
+	"image-to-image": ["diffusers", "transformers.js"],
 	"image-to-text": ["transformers.js"],
 	"image-to-video": ["diffusers"],
 	"video-classification": ["transformers"],
@@ -73,8 +73,8 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"text-generation": ["transformers", "transformers.js"],
 	"text-retrieval": [],
 	"text-to-image": ["diffusers"],
-	"text-to-speech": ["espnet", "tensorflowtts", "transformers"],
-	"text-to-audio": ["transformers"],
+	"text-to-speech": ["espnet", "tensorflowtts", "transformers", "transformers.js"],
+	"text-to-audio": ["transformers", "transformers.js"],
 	"text-to-video": ["diffusers"],
 	"text2text-generation": ["transformers", "transformers.js"],
 	"time-series-forecasting": [],
@@ -89,11 +89,13 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	],
 	translation: ["transformers", "transformers.js"],
 	"unconditional-image-generation": ["diffusers"],
-	"visual-question-answering": ["transformers"],
+	"visual-question-answering": ["transformers", "transformers.js"],
 	"voice-activity-detection": [],
 	"zero-shot-classification": ["transformers", "transformers.js"],
 	"zero-shot-image-classification": ["transformers", "transformers.js"],
-	"zero-shot-object-detection": ["transformers"],
+	"zero-shot-object-detection": ["transformers", "transformers.js"],
+	"text-to-3d": [],
+	"image-to-3d": [],
 };
 
 /**
@@ -161,6 +163,8 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
 	"zero-shot-classification": getData("zero-shot-classification", zeroShotClassification),
 	"zero-shot-image-classification": getData("zero-shot-image-classification", zeroShotImageClassification),
 	"zero-shot-object-detection": getData("zero-shot-object-detection", placeholder),
+	"text-to-3d": getData("text-to-3d", placeholder),
+	"image-to-3d": getData("image-to-3d", placeholder),
 } as const;
 
 export interface ExampleRepo {

package/src/tasks/text-generation/about.md

@@ -32,6 +32,16 @@ The most popular models for this task are GPT-based models, [Mistral](mistralai/
 
 These models are trained to learn the mapping between a pair of texts (e.g. translation from one language to another). The most popular variants of these models are [NLLB](facebook/nllb-200-distilled-600M), [FLAN-T5](https://huggingface.co/google/flan-t5-xxl), and [BART](https://huggingface.co/docs/transformers/model_doc/bart). Text-to-Text models are trained with multi-tasking capabilities, they can accomplish a wide range of tasks, including summarization, translation, and text classification.
 
+## Language Model Variants
+
+When it comes to text generation, the underlying language model can come in several types:
+
+- **Base models:** refers to plain language models like [Mistral 7B](mistralai/Mistral-7B-v0.1) and [Llama-2-70b](https://huggingface.co/meta-llama/Llama-2-70b-hf). These models are good for fine-tuning and few-shot prompting.
+
+- **Instruction-trained models:** these models are trained in a multi-task manner to follow a broad range of instructions like "Write me a recipe for chocolate cake". Models like [Flan-T5](https://huggingface.co/google/flan-t5-xl), [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), and [falcon-40b-instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) are examples of instruction-trained models. In general, instruction-trained models will produce better responses to instructions than base models.
+
+- **Human feedback models:** these models extend base and instruction-trained models by incorporating human feedback that rates the quality of the generated text according to criteria like [helpfulness, honesty, and harmlessness](https://arxiv.org/abs/2112.00861). The human feedback is then combined with an optimization technique like reinforcement learning to align the original model to be closer with human preferences. The overall methodology is often called [Reinforcement Learning from Human Feedback](https://huggingface.co/blog/rlhf), or RLHF for short. [Llama2-Chat](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) is an open-source model aligned through human feedback.
+
 ## Inference
 
 You can use the 🤗 Transformers library `text-generation` pipeline to do inference with Text Generation models. It takes an incomplete text and returns multiple outputs with which the text can be completed.