@huggingface/tasks - npm Package Compare versions

Comparing version 0.0.7 to 0.0.8

dist/index.d.ts

@@ -279,2 +279,6 @@ /**
         name: string;
+        subtasks: {
+            type: string;
+            name: string;
+        }[];
         modality: "cv";
@@ -420,2 +424,12 @@ color: "indigo";
     };
+    "text-to-3d": {
+        name: string;
+        modality: "multimodal";
+        color: "yellow";
+    };
+    "image-to-3d": {
+        name: string;
+        modality: "multimodal";
+        color: "green";
+    };
     other: {
@@ -430,5 +444,5 @@ name: string;
 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">;
 
@@ -764,6 +778,9 @@ /**
 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>>;
@@ -776,2 +793,5 @@ declare function getPythonInferenceSnippet(model: ModelData, accessToken: string): string;
 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 {
@@ -783,6 +803,9 @@ export {
     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,
   };
@@ -789,0 +812,0 @@ }

package.json

 {
   "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",
@@ -33,5 +33,3 @@ "repository": "https://github.com/huggingface/huggingface.js.git",
   "license": "MIT",
-  "devDependencies": {
-    "typescript": "^5.0.4"
-  },
+  "devDependencies": {},
   "scripts": {
@@ -38,0 +36,0 @@ "lint": "eslint --quiet --fix --ext .cjs,.ts .",

src/pipelines.ts

@@ -438,2 +438,16 @@ export const MODALITIES = ["cv", "nlp", "audio", "tabular", "multimodal", "rl", "other"] as const;
 		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",
@@ -625,2 +639,12 @@ color: "indigo",
 	},
+	"text-to-3d": {
+		name: "Text-to-3D",
+		modality: "multimodal",
+		color: "yellow",
+	},
+	"image-to-3d": {
+		name: "Image-to-3D",
+		modality: "multimodal",
+		color: "green",
+	},
 	other: {
@@ -627,0 +651,0 @@ name: "Other",

src/snippets/inputs.ts

@@ -34,2 +34,8 @@ import type { ModelData } from "../model-data";
 
+const inputsVisualQuestionAnswering = () =>
+	`{
+		"image": "cat.png",
+		"question": "What is in this image?"
+	}`;
+
 const inputsQuestionAnswering = () =>
@@ -83,2 +89,7 @@ `{
 
+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: {
@@ -91,2 +102,3 @@ [key in PipelineType]?: (model: ModelData) => string;
 	conversational: inputsConversational,
+	"document-question-answering": inputsVisualQuestionAnswering,
 	"feature-extraction": inputsFeatureExtraction,
@@ -102,2 +114,4 @@ "fill-mask": inputsFillMask,
 	"table-question-answering": inputsTableQuestionAnswering,
+	"tabular-regression": inputsTabularPrediction,
+	"tabular-classification": inputsTabularPrediction,
 	"text-classification": inputsTextClassification,
@@ -112,2 +126,3 @@ "text-generation": inputsTextGeneration,
 	"zero-shot-classification": inputsZeroShotClassification,
+	"zero-shot-image-classification": inputsZeroShotImageClassification,
 };
@@ -114,0 +129,0 @@

src/snippets/python.ts

@@ -15,2 +15,18 @@ import type { ModelData } from "../model-data.js";
 
+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 =>
@@ -46,2 +62,10 @@ `def query(payload):
 
+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 => {
@@ -75,4 +99,17 @@ // Transformers TTS pipeline and api-inference-community (AIC) pipeline outputs are diverged
 };
+
+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,
@@ -98,5 +135,9 @@ "token-classification": snippetBasic,
 	"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,
 };
@@ -103,0 +144,0 @@

src/tasks/index.ts

@@ -43,8 +43,8 @@ import { type PipelineType, PIPELINE_DATA } from "../pipelines";
 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"],
@@ -55,3 +55,3 @@ "fill-mask": ["transformers", "transformers.js"],
 	"image-segmentation": ["transformers", "transformers.js"],
-	"image-to-image": ["diffusers"],
+	"image-to-image": ["diffusers", "transformers.js"],
 	"image-to-text": ["transformers.js"],
@@ -78,4 +78,4 @@ "image-to-video": ["diffusers"],
 	"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"],
@@ -95,7 +95,9 @@ "text2text-generation": ["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": [],
 };
@@ -168,2 +170,4 @@
 	"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;
@@ -170,0 +174,0 @@

src/tasks/text-generation/about.md

@@ -35,2 +35,12 @@ This task covers guides on both [text-generation](https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads) and [text-to-text generation](https://huggingface.co/models?pipeline_tag=text2text-generation&sort=downloads) models. Popular large language models that are used for chats or following instructions are also covered in this task. You can find the list of selected open-source large language models [here](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard), ranked by their performance scores.
 
+## 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
@@ -37,0 +47,0 @@

Fixed alerts

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Dev dependency count

0

decreased by-100%

Number of medium supply chain risk alerts

0

decreased by-100%

Worsened metrics

Total package byte prevSize

769678

decreased by-21%

Number of package files

87

decreased by-1.14%

Lines of code

16837

decreased by-22.51%

No dependency changes