@huggingface/tasks 0.12.26 → 0.12.28

package/dist/index.cjs

@@ -795,7 +795,7 @@ var MAPPING_DEFAULT_WIDGET = /* @__PURE__ */ new Map([
 ]);
 
 // src/pipelines.ts
-var MODALITIES = ["cv", "nlp", "audio", "tabular", "multimodal", "rl", "other"];
+var MODALITIES = ["multimodal", "nlp", "cv", "audio", "tabular", "rl", "other"];
 var MODALITY_LABELS = {
   multimodal: "Multimodal",
   nlp: "Natural Language Processing",
@@ -5797,6 +5797,12 @@ var MODEL_LIBRARIES_UI_ELEMENTS = {
     repoUrl: "https://github.com/abetlen/llama-cpp-python",
     snippets: llama_cpp_python
   },
+  "mini-omni2": {
+    prettyLabel: "Mini-Omni2",
+    repoName: "Mini-Omni2",
+    repoUrl: "https://github.com/gpt-omni/mini-omni2",
+    countDownloads: `path:"model_config.yaml"`
+  },
   mindspore: {
     prettyLabel: "MindSpore",
     repoName: "mindspore",
@@ -6250,7 +6256,28 @@ var inputsQuestionAnswering = () => `{
 }`;
 var inputsTextClassification = () => `"I like you. I love you"`;
 var inputsTokenClassification = () => `"My name is Sarah Jessica Parker but you can call me Jessica"`;
-var inputsTextGeneration = () => `"Can you please let us know more details about your "`;
+var inputsTextGeneration = (model) => {
+  if (model.tags.includes("conversational")) {
+    return model.pipeline_tag === "text-generation" ? [{ role: "user", content: "What is the capital of France?" }] : [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "Describe this image in one sentence."
+          },
+          {
+            type: "image_url",
+            image_url: {
+              url: "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
+            }
+          }
+        ]
+      }
+    ];
+  }
+  return `"Can you please let us know more details about your "`;
+};
 var inputsText2TextGeneration = () => `"The answer to the universe is"`;
 var inputsFillMask = (model) => `"The answer to the universe is ${model.mask_token}."`;
 var inputsSentenceSimilarity = () => `{
@@ -6307,13 +6334,15 @@ function getModelInputSnippet(model, noWrap = false, noQuotes = false) {
     const inputs = modelInputSnippets[model.pipeline_tag];
     if (inputs) {
       let result = inputs(model);
-      if (noWrap) {
-        result = result.replace(/(?:(?:\r?\n|\r)\t*)|\t+/g, " ");
-      }
-      if (noQuotes) {
-        const REGEX_QUOTES = /^"(.+)"$/s;
-        const match = result.match(REGEX_QUOTES);
-        result = match ? match[1] : result;
+      if (typeof result === "string") {
+        if (noWrap) {
+          result = result.replace(/(?:(?:\r?\n|\r)\t*)|\t+/g, " ");
+        }
+        if (noQuotes) {
+          const REGEX_QUOTES = /^"(.+)"$/s;
+          const match = result.match(REGEX_QUOTES);
+          result = match ? match[1] : result;
+        }
       }
       return result;
     }
@@ -6329,7 +6358,6 @@ __export(curl_exports, {
   hasCurlInferenceSnippet: () => hasCurlInferenceSnippet,
   snippetBasic: () => snippetBasic,
   snippetFile: () => snippetFile,
-  snippetImageTextToTextGeneration: () => snippetImageTextToTextGeneration,
   snippetTextGeneration: () => snippetTextGeneration,
   snippetZeroShotClassification: () => snippetZeroShotClassification
 });
@@ -6377,9 +6405,8 @@ var snippetBasic = (model, accessToken) => ({
 var snippetTextGeneration = (model, accessToken, opts) => {
   if (model.tags.includes("conversational")) {
     const streaming = opts?.streaming ?? true;
-    const messages = opts?.messages ?? [
-      { role: "user", content: "What is the capital of France?" }
-    ];
+    const exampleMessages = getModelInputSnippet(model);
+    const messages = opts?.messages ?? exampleMessages;
     const config = {
       ...opts?.temperature ? { temperature: opts.temperature } : void 0,
       max_tokens: opts?.max_tokens ?? 500,
@@ -6414,32 +6441,6 @@ var snippetTextGeneration = (model, accessToken, opts) => {
     return snippetBasic(model, accessToken);
   }
 };
-var snippetImageTextToTextGeneration = (model, accessToken) => {
-  if (model.tags.includes("conversational")) {
-    return {
-      content: `curl 'https://api-inference.huggingface.co/models/${model.id}/v1/chat/completions' \\
--H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}" \\
--H 'Content-Type: application/json' \\
--d '{
-	"model": "${model.id}",
-	"messages": [
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"}},
-				{"type": "text", "text": "Describe this image in one sentence."}
-			]
-		}
-	],
-	"max_tokens": 500,
-	"stream": false
-}'
-`
-    };
-  } else {
-    return snippetBasic(model, accessToken);
-  }
-};
 var snippetZeroShotClassification = (model, accessToken) => ({
   content: `curl https://api-inference.huggingface.co/models/${model.id} \\
 	-X POST \\
@@ -6464,7 +6465,7 @@ var curlSnippets = {
   summarization: snippetBasic,
   "feature-extraction": snippetBasic,
   "text-generation": snippetTextGeneration,
-  "image-text-to-text": snippetImageTextToTextGeneration,
+  "image-text-to-text": snippetTextGeneration,
   "text2text-generation": snippetBasic,
   "fill-mask": snippetBasic,
   "sentence-similarity": snippetBasic,
@@ -6494,7 +6495,6 @@ __export(python_exports, {
   pythonSnippets: () => pythonSnippets,
   snippetBasic: () => snippetBasic2,
   snippetConversational: () => snippetConversational,
-  snippetConversationalWithImage: () => snippetConversationalWithImage,
   snippetDocumentQuestionAnswering: () => snippetDocumentQuestionAnswering,
   snippetFile: () => snippetFile2,
   snippetTabular: () => snippetTabular,
@@ -6505,9 +6505,8 @@ __export(python_exports, {
 });
 var snippetConversational = (model, accessToken, opts) => {
   const streaming = opts?.streaming ?? true;
-  const messages = opts?.messages ?? [
-    { role: "user", content: "What is the capital of France?" }
-  ];
+  const exampleMessages = getModelInputSnippet(model);
+  const messages = opts?.messages ?? exampleMessages;
   const messagesStr = stringifyMessages(messages, {
     sep: ",\n	",
     start: `[
@@ -6609,29 +6608,6 @@ print(completion.choices[0].message)`
     ];
   }
 };
-var snippetConversationalWithImage = (model, accessToken) => ({
-  content: `from huggingface_hub import InferenceClient
-
-client = InferenceClient(api_key="${accessToken || "{API_TOKEN}"}")
-
-image_url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
-
-for message in client.chat_completion(
-	model="${model.id}",
-	messages=[
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": image_url}},
-				{"type": "text", "text": "Describe this image in one sentence."},
-			],
-		}
-	],
-	max_tokens=500,
-	stream=True,
-):
-	print(message.choices[0].delta.content, end="")`
-});
 var snippetZeroShotClassification2 = (model) => ({
   content: `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
@@ -6749,7 +6725,7 @@ var pythonSnippets = {
   "feature-extraction": snippetBasic2,
   "text-generation": snippetBasic2,
   "text2text-generation": snippetBasic2,
-  "image-text-to-text": snippetConversationalWithImage,
+  "image-text-to-text": snippetConversational,
   "fill-mask": snippetBasic2,
   "sentence-similarity": snippetBasic2,
   "automatic-speech-recognition": snippetFile2,
@@ -6768,10 +6744,8 @@ var pythonSnippets = {
   "zero-shot-image-classification": snippetZeroShotImageClassification
 };
 function getPythonInferenceSnippet(model, accessToken, opts) {
-  if (model.pipeline_tag === "text-generation" && model.tags.includes("conversational")) {
+  if (model.tags.includes("conversational")) {
     return snippetConversational(model, accessToken, opts);
-  } else if (model.pipeline_tag === "image-text-to-text" && model.tags.includes("conversational")) {
-    return snippetConversationalWithImage(model, accessToken);
   } else {
     let snippets = model.pipeline_tag && model.pipeline_tag in pythonSnippets ? pythonSnippets[model.pipeline_tag]?.(model, accessToken) ?? { content: "" } : { content: "" };
     snippets = Array.isArray(snippets) ? snippets : [snippets];
@@ -6800,7 +6774,6 @@ __export(js_exports, {
   jsSnippets: () => jsSnippets,
   snippetBasic: () => snippetBasic3,
   snippetFile: () => snippetFile3,
-  snippetImageTextToTextGeneration: () => snippetImageTextToTextGeneration2,
   snippetTextGeneration: () => snippetTextGeneration2,
   snippetTextToAudio: () => snippetTextToAudio2,
   snippetTextToImage: () => snippetTextToImage2,
@@ -6830,9 +6803,8 @@ query({"inputs": ${getModelInputSnippet(model)}}).then((response) => {
 var snippetTextGeneration2 = (model, accessToken, opts) => {
   if (model.tags.includes("conversational")) {
     const streaming = opts?.streaming ?? true;
-    const messages = opts?.messages ?? [
-      { role: "user", content: "What is the capital of France?" }
-    ];
+    const exampleMessages = getModelInputSnippet(model);
+    const messages = opts?.messages ?? exampleMessages;
     const messagesStr = stringifyMessages(messages, { sep: ",\n		", start: "[\n		", end: "\n	]" });
     const config = {
       ...opts?.temperature ? { temperature: opts.temperature } : void 0,
@@ -6935,34 +6907,6 @@ console.log(chatCompletion.choices[0].message);`
     return snippetBasic3(model, accessToken);
   }
 };
-var snippetImageTextToTextGeneration2 = (model, accessToken) => {
-  if (model.tags.includes("conversational")) {
-    return {
-      content: `import { HfInference } from "@huggingface/inference";
-
-const inference = new HfInference("${accessToken || `{API_TOKEN}`}");
-const imageUrl = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg";
-
-for await (const chunk of inference.chatCompletionStream({
-	model: "${model.id}",
-	messages: [
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": imageUrl}},
-				{"type": "text", "text": "Describe this image in one sentence."},
-			],
-		}
-	],
-	max_tokens: 500,
-})) {
-	process.stdout.write(chunk.choices[0]?.delta?.content || "");
-}`
-    };
-  } else {
-    return snippetBasic3(model, accessToken);
-  }
-};
 var snippetZeroShotClassification3 = (model, accessToken) => ({
   content: `async function query(data) {
 	const response = await fetch(
@@ -7075,7 +7019,7 @@ var jsSnippets = {
   summarization: snippetBasic3,
   "feature-extraction": snippetBasic3,
   "text-generation": snippetTextGeneration2,
-  "image-text-to-text": snippetImageTextToTextGeneration2,
+  "image-text-to-text": snippetTextGeneration2,
   "text2text-generation": snippetBasic3,
   "fill-mask": snippetBasic3,
   "sentence-similarity": snippetBasic3,

package/dist/index.js

@@ -757,7 +757,7 @@ var MAPPING_DEFAULT_WIDGET = /* @__PURE__ */ new Map([
 ]);
 
 // src/pipelines.ts
-var MODALITIES = ["cv", "nlp", "audio", "tabular", "multimodal", "rl", "other"];
+var MODALITIES = ["multimodal", "nlp", "cv", "audio", "tabular", "rl", "other"];
 var MODALITY_LABELS = {
   multimodal: "Multimodal",
   nlp: "Natural Language Processing",
@@ -5759,6 +5759,12 @@ var MODEL_LIBRARIES_UI_ELEMENTS = {
     repoUrl: "https://github.com/abetlen/llama-cpp-python",
     snippets: llama_cpp_python
   },
+  "mini-omni2": {
+    prettyLabel: "Mini-Omni2",
+    repoName: "Mini-Omni2",
+    repoUrl: "https://github.com/gpt-omni/mini-omni2",
+    countDownloads: `path:"model_config.yaml"`
+  },
   mindspore: {
     prettyLabel: "MindSpore",
     repoName: "mindspore",
@@ -6212,7 +6218,28 @@ var inputsQuestionAnswering = () => `{
 }`;
 var inputsTextClassification = () => `"I like you. I love you"`;
 var inputsTokenClassification = () => `"My name is Sarah Jessica Parker but you can call me Jessica"`;
-var inputsTextGeneration = () => `"Can you please let us know more details about your "`;
+var inputsTextGeneration = (model) => {
+  if (model.tags.includes("conversational")) {
+    return model.pipeline_tag === "text-generation" ? [{ role: "user", content: "What is the capital of France?" }] : [
+      {
+        role: "user",
+        content: [
+          {
+            type: "text",
+            text: "Describe this image in one sentence."
+          },
+          {
+            type: "image_url",
+            image_url: {
+              url: "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
+            }
+          }
+        ]
+      }
+    ];
+  }
+  return `"Can you please let us know more details about your "`;
+};
 var inputsText2TextGeneration = () => `"The answer to the universe is"`;
 var inputsFillMask = (model) => `"The answer to the universe is ${model.mask_token}."`;
 var inputsSentenceSimilarity = () => `{
@@ -6269,13 +6296,15 @@ function getModelInputSnippet(model, noWrap = false, noQuotes = false) {
     const inputs = modelInputSnippets[model.pipeline_tag];
     if (inputs) {
       let result = inputs(model);
-      if (noWrap) {
-        result = result.replace(/(?:(?:\r?\n|\r)\t*)|\t+/g, " ");
-      }
-      if (noQuotes) {
-        const REGEX_QUOTES = /^"(.+)"$/s;
-        const match = result.match(REGEX_QUOTES);
-        result = match ? match[1] : result;
+      if (typeof result === "string") {
+        if (noWrap) {
+          result = result.replace(/(?:(?:\r?\n|\r)\t*)|\t+/g, " ");
+        }
+        if (noQuotes) {
+          const REGEX_QUOTES = /^"(.+)"$/s;
+          const match = result.match(REGEX_QUOTES);
+          result = match ? match[1] : result;
+        }
       }
       return result;
     }
@@ -6291,7 +6320,6 @@ __export(curl_exports, {
   hasCurlInferenceSnippet: () => hasCurlInferenceSnippet,
   snippetBasic: () => snippetBasic,
   snippetFile: () => snippetFile,
-  snippetImageTextToTextGeneration: () => snippetImageTextToTextGeneration,
   snippetTextGeneration: () => snippetTextGeneration,
   snippetZeroShotClassification: () => snippetZeroShotClassification
 });
@@ -6339,9 +6367,8 @@ var snippetBasic = (model, accessToken) => ({
 var snippetTextGeneration = (model, accessToken, opts) => {
   if (model.tags.includes("conversational")) {
     const streaming = opts?.streaming ?? true;
-    const messages = opts?.messages ?? [
-      { role: "user", content: "What is the capital of France?" }
-    ];
+    const exampleMessages = getModelInputSnippet(model);
+    const messages = opts?.messages ?? exampleMessages;
     const config = {
       ...opts?.temperature ? { temperature: opts.temperature } : void 0,
       max_tokens: opts?.max_tokens ?? 500,
@@ -6376,32 +6403,6 @@ var snippetTextGeneration = (model, accessToken, opts) => {
     return snippetBasic(model, accessToken);
   }
 };
-var snippetImageTextToTextGeneration = (model, accessToken) => {
-  if (model.tags.includes("conversational")) {
-    return {
-      content: `curl 'https://api-inference.huggingface.co/models/${model.id}/v1/chat/completions' \\
--H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}" \\
--H 'Content-Type: application/json' \\
--d '{
-	"model": "${model.id}",
-	"messages": [
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"}},
-				{"type": "text", "text": "Describe this image in one sentence."}
-			]
-		}
-	],
-	"max_tokens": 500,
-	"stream": false
-}'
-`
-    };
-  } else {
-    return snippetBasic(model, accessToken);
-  }
-};
 var snippetZeroShotClassification = (model, accessToken) => ({
   content: `curl https://api-inference.huggingface.co/models/${model.id} \\
 	-X POST \\
@@ -6426,7 +6427,7 @@ var curlSnippets = {
   summarization: snippetBasic,
   "feature-extraction": snippetBasic,
   "text-generation": snippetTextGeneration,
-  "image-text-to-text": snippetImageTextToTextGeneration,
+  "image-text-to-text": snippetTextGeneration,
   "text2text-generation": snippetBasic,
   "fill-mask": snippetBasic,
   "sentence-similarity": snippetBasic,
@@ -6456,7 +6457,6 @@ __export(python_exports, {
   pythonSnippets: () => pythonSnippets,
   snippetBasic: () => snippetBasic2,
   snippetConversational: () => snippetConversational,
-  snippetConversationalWithImage: () => snippetConversationalWithImage,
   snippetDocumentQuestionAnswering: () => snippetDocumentQuestionAnswering,
   snippetFile: () => snippetFile2,
   snippetTabular: () => snippetTabular,
@@ -6467,9 +6467,8 @@ __export(python_exports, {
 });
 var snippetConversational = (model, accessToken, opts) => {
   const streaming = opts?.streaming ?? true;
-  const messages = opts?.messages ?? [
-    { role: "user", content: "What is the capital of France?" }
-  ];
+  const exampleMessages = getModelInputSnippet(model);
+  const messages = opts?.messages ?? exampleMessages;
   const messagesStr = stringifyMessages(messages, {
     sep: ",\n	",
     start: `[
@@ -6571,29 +6570,6 @@ print(completion.choices[0].message)`
     ];
   }
 };
-var snippetConversationalWithImage = (model, accessToken) => ({
-  content: `from huggingface_hub import InferenceClient
-
-client = InferenceClient(api_key="${accessToken || "{API_TOKEN}"}")
-
-image_url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
-
-for message in client.chat_completion(
-	model="${model.id}",
-	messages=[
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": image_url}},
-				{"type": "text", "text": "Describe this image in one sentence."},
-			],
-		}
-	],
-	max_tokens=500,
-	stream=True,
-):
-	print(message.choices[0].delta.content, end="")`
-});
 var snippetZeroShotClassification2 = (model) => ({
   content: `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
@@ -6711,7 +6687,7 @@ var pythonSnippets = {
   "feature-extraction": snippetBasic2,
   "text-generation": snippetBasic2,
   "text2text-generation": snippetBasic2,
-  "image-text-to-text": snippetConversationalWithImage,
+  "image-text-to-text": snippetConversational,
   "fill-mask": snippetBasic2,
   "sentence-similarity": snippetBasic2,
   "automatic-speech-recognition": snippetFile2,
@@ -6730,10 +6706,8 @@ var pythonSnippets = {
   "zero-shot-image-classification": snippetZeroShotImageClassification
 };
 function getPythonInferenceSnippet(model, accessToken, opts) {
-  if (model.pipeline_tag === "text-generation" && model.tags.includes("conversational")) {
+  if (model.tags.includes("conversational")) {
     return snippetConversational(model, accessToken, opts);
-  } else if (model.pipeline_tag === "image-text-to-text" && model.tags.includes("conversational")) {
-    return snippetConversationalWithImage(model, accessToken);
   } else {
     let snippets = model.pipeline_tag && model.pipeline_tag in pythonSnippets ? pythonSnippets[model.pipeline_tag]?.(model, accessToken) ?? { content: "" } : { content: "" };
     snippets = Array.isArray(snippets) ? snippets : [snippets];
@@ -6762,7 +6736,6 @@ __export(js_exports, {
   jsSnippets: () => jsSnippets,
   snippetBasic: () => snippetBasic3,
   snippetFile: () => snippetFile3,
-  snippetImageTextToTextGeneration: () => snippetImageTextToTextGeneration2,
   snippetTextGeneration: () => snippetTextGeneration2,
   snippetTextToAudio: () => snippetTextToAudio2,
   snippetTextToImage: () => snippetTextToImage2,
@@ -6792,9 +6765,8 @@ query({"inputs": ${getModelInputSnippet(model)}}).then((response) => {
 var snippetTextGeneration2 = (model, accessToken, opts) => {
   if (model.tags.includes("conversational")) {
     const streaming = opts?.streaming ?? true;
-    const messages = opts?.messages ?? [
-      { role: "user", content: "What is the capital of France?" }
-    ];
+    const exampleMessages = getModelInputSnippet(model);
+    const messages = opts?.messages ?? exampleMessages;
     const messagesStr = stringifyMessages(messages, { sep: ",\n		", start: "[\n		", end: "\n	]" });
     const config = {
       ...opts?.temperature ? { temperature: opts.temperature } : void 0,
@@ -6897,34 +6869,6 @@ console.log(chatCompletion.choices[0].message);`
     return snippetBasic3(model, accessToken);
   }
 };
-var snippetImageTextToTextGeneration2 = (model, accessToken) => {
-  if (model.tags.includes("conversational")) {
-    return {
-      content: `import { HfInference } from "@huggingface/inference";
-
-const inference = new HfInference("${accessToken || `{API_TOKEN}`}");
-const imageUrl = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg";
-
-for await (const chunk of inference.chatCompletionStream({
-	model: "${model.id}",
-	messages: [
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": imageUrl}},
-				{"type": "text", "text": "Describe this image in one sentence."},
-			],
-		}
-	],
-	max_tokens: 500,
-})) {
-	process.stdout.write(chunk.choices[0]?.delta?.content || "");
-}`
-    };
-  } else {
-    return snippetBasic3(model, accessToken);
-  }
-};
 var snippetZeroShotClassification3 = (model, accessToken) => ({
   content: `async function query(data) {
 	const response = await fetch(
@@ -7037,7 +6981,7 @@ var jsSnippets = {
   summarization: snippetBasic3,
   "feature-extraction": snippetBasic3,
   "text-generation": snippetTextGeneration2,
-  "image-text-to-text": snippetImageTextToTextGeneration2,
+  "image-text-to-text": snippetTextGeneration2,
   "text2text-generation": snippetBasic3,
   "fill-mask": snippetBasic3,
   "sentence-similarity": snippetBasic3,

package/dist/src/model-libraries.d.ts

@@ -367,6 +367,12 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         repoUrl: string;
         snippets: (model: ModelData) => string[];
     };
+    "mini-omni2": {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        countDownloads: string;
+    };
     mindspore: {
         prettyLabel: string;
         repoName: string;
@@ -766,6 +772,6 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
     };
 };
 export type ModelLibraryKey = keyof typeof MODEL_LIBRARIES_UI_ELEMENTS;
-export declare const ALL_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "deepforest" | "depth-anything-v2" | "depth-pro" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "hunyuan-dit" | "imstoucan" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "liveportrait" | "llama-cpp-python" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pxia" | "pyannote-audio" | "py-feat" | "pythae" | "recurrentgemma" | "relik" | "refiners" | "reverb" | "saelens" | "sam2" | "sample-factory" | "sapiens" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "ssr-speech" | "stable-audio-tools" | "diffusion-single-file" | "seed-story" | "soloaudio" | "stable-baselines3" | "stanza" | "f5-tts" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "vfi-mamba" | "voicecraft" | "yolov10" | "whisperkit" | "3dtopia-xl")[];
-export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "deepforest" | "depth-anything-v2" | "depth-pro" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "hunyuan-dit" | "imstoucan" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "liveportrait" | "llama-cpp-python" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pxia" | "pyannote-audio" | "py-feat" | "pythae" | "recurrentgemma" | "relik" | "refiners" | "reverb" | "saelens" | "sam2" | "sample-factory" | "sapiens" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "ssr-speech" | "stable-audio-tools" | "diffusion-single-file" | "seed-story" | "soloaudio" | "stable-baselines3" | "stanza" | "f5-tts" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "vfi-mamba" | "voicecraft" | "yolov10" | "whisperkit" | "3dtopia-xl")[];
+export declare const ALL_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "deepforest" | "depth-anything-v2" | "depth-pro" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "hunyuan-dit" | "imstoucan" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "liveportrait" | "llama-cpp-python" | "mini-omni2" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pxia" | "pyannote-audio" | "py-feat" | "pythae" | "recurrentgemma" | "relik" | "refiners" | "reverb" | "saelens" | "sam2" | "sample-factory" | "sapiens" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "ssr-speech" | "stable-audio-tools" | "diffusion-single-file" | "seed-story" | "soloaudio" | "stable-baselines3" | "stanza" | "f5-tts" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "vfi-mamba" | "voicecraft" | "yolov10" | "whisperkit" | "3dtopia-xl")[];
+export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "deepforest" | "depth-anything-v2" | "depth-pro" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "hunyuan-dit" | "imstoucan" | "keras" | "tf-keras" | "keras-nlp" | "k2" | "liveportrait" | "llama-cpp-python" | "mini-omni2" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pxia" | "pyannote-audio" | "py-feat" | "pythae" | "recurrentgemma" | "relik" | "refiners" | "reverb" | "saelens" | "sam2" | "sample-factory" | "sapiens" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "ssr-speech" | "stable-audio-tools" | "diffusion-single-file" | "seed-story" | "soloaudio" | "stable-baselines3" | "stanza" | "f5-tts" | "tensorflowtts" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "vfi-mamba" | "voicecraft" | "yolov10" | "whisperkit" | "3dtopia-xl")[];
 //# sourceMappingURL=model-libraries.d.ts.map

package/dist/src/model-libraries.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"model-libraries.d.ts","sourceRoot":"","sources":["../../src/model-libraries.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAC9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,6BAA6B,CAAC;AAEtE;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,QAAQ,CAAC,EAAE,CAAC,KAAK,EAAE,SAAS,KAAK,MAAM,EAAE,CAAC;IAC1C;;;;;OAKG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;OAGG;IACH,MAAM,CAAC,EAAE,OAAO,CAAC;CACjB;AAED;;;;;;;;;;;;;GAaG;AAEH,eAAO,MAAM,2BAA2B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAysBI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,yyCAAgE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,yyCAQ1B,CAAC"}
+{"version":3,"file":"model-libraries.d.ts","sourceRoot":"","sources":["../../src/model-libraries.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAC9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,6BAA6B,CAAC;AAEtE;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,QAAQ,CAAC,EAAE,CAAC,KAAK,EAAE,SAAS,KAAK,MAAM,EAAE,CAAC;IAC1C;;;;;OAKG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;OAGG;IACH,MAAM,CAAC,EAAE,OAAO,CAAC;CACjB;AAED;;;;;;;;;;;;;GAaG;AAEH,eAAO,MAAM,2BAA2B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA+sBI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,wzCAAgE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,wzCAQ1B,CAAC"}

package/dist/src/pipelines.d.ts

@@ -1,4 +1,4 @@
-export declare const MODALITIES: readonly ["cv", "nlp", "audio", "tabular", "multimodal", "rl", "other"];
+export declare const MODALITIES: readonly ["multimodal", "nlp", "cv", "audio", "tabular", "rl", "other"];
 export type Modality = (typeof MODALITIES)[number];
 export declare const MODALITY_LABELS: {
     multimodal: string;

package/dist/src/snippets/curl.d.ts

@@ -9,7 +9,6 @@ export declare const snippetTextGeneration: (model: ModelDataMinimal, accessToke
     max_tokens?: GenerationParameters["max_tokens"];
     top_p?: GenerationParameters["top_p"];
 }) => InferenceSnippet;
-export declare const snippetImageTextToTextGeneration: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const snippetZeroShotClassification: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const snippetFile: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const curlSnippets: Partial<Record<PipelineType, (model: ModelDataMinimal, accessToken: string, opts?: Record<string, unknown>) => InferenceSnippet>>;

package/dist/src/snippets/curl.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"curl.d.ts","sourceRoot":"","sources":["../../../src/snippets/curl.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AACpD,OAAO,KAAK,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,MAAM,mBAAmB,CAAC;AAG1F,OAAO,KAAK,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAErE,eAAO,MAAM,YAAY,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAM1E,CAAC;AAEH,eAAO,MAAM,qBAAqB,UAC1B,gBAAgB,eACV,MAAM,SACZ;IACN,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,0BAA0B,EAAE,CAAC;IACxC,WAAW,CAAC,EAAE,oBAAoB,CAAC,aAAa,CAAC,CAAC;IAClD,UAAU,CAAC,EAAE,oBAAoB,CAAC,YAAY,CAAC,CAAC;IAChD,KAAK,CAAC,EAAE,oBAAoB,CAAC,OAAO,CAAC,CAAC;CACtC,KACC,gBAuCF,CAAC;AAEF,eAAO,MAAM,gCAAgC,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBA0B/F,CAAC;AAEF,eAAO,MAAM,6BAA6B,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAM3F,CAAC;AAEH,eAAO,MAAM,WAAW,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAKzE,CAAC;AAEH,eAAO,MAAM,YAAY,EAAE,OAAO,CACjC,MAAM,CACL,YAAY,EACZ,CAAC,KAAK,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAAK,gBAAgB,CAClG,CA0BD,CAAC;AAEF,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,GAAG,gBAAgB,CAItG;AAED,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,IAAI,CAAC,gBAAgB,EAAE,cAAc,CAAC,GAAG,OAAO,CAE9F"}
+{"version":3,"file":"curl.d.ts","sourceRoot":"","sources":["../../../src/snippets/curl.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AACpD,OAAO,KAAK,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,MAAM,mBAAmB,CAAC;AAG1F,OAAO,KAAK,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAErE,eAAO,MAAM,YAAY,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAM1E,CAAC;AAEH,eAAO,MAAM,qBAAqB,UAC1B,gBAAgB,eACV,MAAM,SACZ;IACN,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,0BAA0B,EAAE,CAAC;IACxC,WAAW,CAAC,EAAE,oBAAoB,CAAC,aAAa,CAAC,CAAC;IAClD,UAAU,CAAC,EAAE,oBAAoB,CAAC,YAAY,CAAC,CAAC;IAChD,KAAK,CAAC,EAAE,oBAAoB,CAAC,OAAO,CAAC,CAAC;CACtC,KACC,gBAsCF,CAAC;AAEF,eAAO,MAAM,6BAA6B,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAM3F,CAAC;AAEH,eAAO,MAAM,WAAW,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAKzE,CAAC;AAEH,eAAO,MAAM,YAAY,EAAE,OAAO,CACjC,MAAM,CACL,YAAY,EACZ,CAAC,KAAK,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAAK,gBAAgB,CAClG,CA0BD,CAAC;AAEF,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,GAAG,gBAAgB,CAItG;AAED,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,IAAI,CAAC,gBAAgB,EAAE,cAAc,CAAC,GAAG,OAAO,CAE9F"}

package/dist/src/snippets/inputs.d.ts

@@ -1,3 +1,4 @@
+import type { ChatCompletionInputMessage } from "../tasks";
 import type { ModelDataMinimal } from "./types";
-export declare function getModelInputSnippet(model: ModelDataMinimal, noWrap?: boolean, noQuotes?: boolean): string;
+export declare function getModelInputSnippet(model: ModelDataMinimal, noWrap?: boolean, noQuotes?: boolean): string | ChatCompletionInputMessage[];
 //# sourceMappingURL=inputs.d.ts.map

package/dist/src/snippets/inputs.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inputs.d.ts","sourceRoot":"","sources":["../../../src/snippets/inputs.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,SAAS,CAAC;AAqHhD,wBAAgB,oBAAoB,CAAC,KAAK,EAAE,gBAAgB,EAAE,MAAM,UAAQ,EAAE,QAAQ,UAAQ,GAAG,MAAM,CAiBtG"}
+{"version":3,"file":"inputs.d.ts","sourceRoot":"","sources":["../../../src/snippets/inputs.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,0BAA0B,EAAE,MAAM,UAAU,CAAC;AAC3D,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,SAAS,CAAC;AA4IhD,wBAAgB,oBAAoB,CACnC,KAAK,EAAE,gBAAgB,EACvB,MAAM,UAAQ,EACd,QAAQ,UAAQ,GACd,MAAM,GAAG,0BAA0B,EAAE,CAmBvC"}

package/dist/src/snippets/js.d.ts

@@ -9,7 +9,6 @@ export declare const snippetTextGeneration: (model: ModelDataMinimal, accessToke
     max_tokens?: GenerationParameters["max_tokens"];
     top_p?: GenerationParameters["top_p"];
 }) => InferenceSnippet | InferenceSnippet[];
-export declare const snippetImageTextToTextGeneration: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const snippetZeroShotClassification: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const snippetTextToImage: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const snippetTextToAudio: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;

package/dist/src/snippets/js.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"js.d.ts","sourceRoot":"","sources":["../../../src/snippets/js.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AACpD,OAAO,KAAK,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,MAAM,mBAAmB,CAAC;AAG1F,OAAO,KAAK,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAErE,eAAO,MAAM,YAAY,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAoB1E,CAAC;AAEH,eAAO,MAAM,qBAAqB,UAC1B,gBAAgB,eACV,MAAM,SACZ;IACN,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,0BAA0B,EAAE,CAAC;IACxC,WAAW,CAAC,EAAE,oBAAoB,CAAC,aAAa,CAAC,CAAC;IAClD,UAAU,CAAC,EAAE,oBAAoB,CAAC,YAAY,CAAC,CAAC;IAChD,KAAK,CAAC,EAAE,oBAAoB,CAAC,OAAO,CAAC,CAAC;CACtC,KACC,gBAAgB,GAAG,gBAAgB,EA8GrC,CAAC;AAEF,eAAO,MAAM,gCAAgC,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBA4B/F,CAAC;AAEF,eAAO,MAAM,6BAA6B,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAsB3F,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAmBhF,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAuCjF,CAAC;AAEF,eAAO,MAAM,WAAW,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAqBzE,CAAC;AAEH,eAAO,MAAM,UAAU,EAAE,OAAO,CAC/B,MAAM,CACL,YAAY,EACZ,CACC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,EACnB,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAC1B,gBAAgB,GAAG,gBAAgB,EAAE,CAC1C,CA0BD,CAAC;AAEF,wBAAgB,qBAAqB,CACpC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,GACjB,gBAAgB,GAAG,gBAAgB,EAAE,CAIvC;AAED,wBAAgB,qBAAqB,CAAC,KAAK,EAAE,gBAAgB,GAAG,OAAO,CAEtE"}
+{"version":3,"file":"js.d.ts","sourceRoot":"","sources":["../../../src/snippets/js.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AACpD,OAAO,KAAK,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,MAAM,mBAAmB,CAAC;AAG1F,OAAO,KAAK,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAErE,eAAO,MAAM,YAAY,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAoB1E,CAAC;AAEH,eAAO,MAAM,qBAAqB,UAC1B,gBAAgB,eACV,MAAM,SACZ;IACN,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,0BAA0B,EAAE,CAAC;IACxC,WAAW,CAAC,EAAE,oBAAoB,CAAC,aAAa,CAAC,CAAC;IAClD,UAAU,CAAC,EAAE,oBAAoB,CAAC,YAAY,CAAC,CAAC;IAChD,KAAK,CAAC,EAAE,oBAAoB,CAAC,OAAO,CAAC,CAAC;CACtC,KACC,gBAAgB,GAAG,gBAAgB,EA6GrC,CAAC;AAEF,eAAO,MAAM,6BAA6B,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAsB3F,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAmBhF,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAuCjF,CAAC;AAEF,eAAO,MAAM,WAAW,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAqBzE,CAAC;AAEH,eAAO,MAAM,UAAU,EAAE,OAAO,CAC/B,MAAM,CACL,YAAY,EACZ,CACC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,EACnB,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAC1B,gBAAgB,GAAG,gBAAgB,EAAE,CAC1C,CA0BD,CAAC;AAEF,wBAAgB,qBAAqB,CACpC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,GACjB,gBAAgB,GAAG,gBAAgB,EAAE,CAIvC;AAED,wBAAgB,qBAAqB,CAAC,KAAK,EAAE,gBAAgB,GAAG,OAAO,CAEtE"}

package/dist/src/snippets/python.d.ts

@@ -8,7 +8,6 @@ export declare const snippetConversational: (model: ModelDataMinimal, accessToke
     max_tokens?: GenerationParameters["max_tokens"];
     top_p?: GenerationParameters["top_p"];
 }) => InferenceSnippet[];
-export declare const snippetConversationalWithImage: (model: ModelDataMinimal, accessToken: string) => InferenceSnippet;
 export declare const snippetZeroShotClassification: (model: ModelDataMinimal) => InferenceSnippet;
 export declare const snippetZeroShotImageClassification: (model: ModelDataMinimal) => InferenceSnippet;
 export declare const snippetBasic: (model: ModelDataMinimal) => InferenceSnippet;

package/dist/src/snippets/python.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"python.d.ts","sourceRoot":"","sources":["../../../src/snippets/python.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AACpD,OAAO,KAAK,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,MAAM,mBAAmB,CAAC;AAG1F,OAAO,KAAK,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAErE,eAAO,MAAM,qBAAqB,UAC1B,gBAAgB,eACV,MAAM,SACZ;IACN,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,0BAA0B,EAAE,CAAC;IACxC,WAAW,CAAC,EAAE,oBAAoB,CAAC,aAAa,CAAC,CAAC;IAClD,UAAU,CAAC,EAAE,oBAAoB,CAAC,YAAY,CAAC,CAAC;IAChD,KAAK,CAAC,EAAE,oBAAoB,CAAC,OAAO,CAAC,CAAC;CACtC,KACC,gBAAgB,EAyGlB,CAAC;AAEF,eAAO,MAAM,8BAA8B,UAAW,gBAAgB,eAAe,MAAM,KAAG,gBAsB5F,CAAC;AAEH,eAAO,MAAM,6BAA6B,UAAW,gBAAgB,KAAG,gBAStE,CAAC;AAEH,eAAO,MAAM,kCAAkC,UAAW,gBAAgB,KAAG,gBAe3E,CAAC;AAEH,eAAO,MAAM,YAAY,UAAW,gBAAgB,KAAG,gBAQrD,CAAC;AAEH,eAAO,MAAM,WAAW,UAAW,gBAAgB,KAAG,gBAQpD,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,KAAG,gBAW3D,CAAC;AAEH,eAAO,MAAM,cAAc,UAAW,gBAAgB,KAAG,gBAOvD,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,KAAG,gBA+B5D,CAAC;AAEF,eAAO,MAAM,gCAAgC,UAAW,gBAAgB,KAAG,gBAWzE,CAAC;AAEH,eAAO,MAAM,cAAc,EAAE,OAAO,CACnC,MAAM,CACL,YAAY,EACZ,CACC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,EACnB,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAC1B,gBAAgB,GAAG,gBAAgB,EAAE,CAC1C,CA8BD,CAAC;AAEF,wBAAgB,yBAAyB,CACxC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,EACnB,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAC5B,gBAAgB,GAAG,gBAAgB,EAAE,CA2BvC;AAED,wBAAgB,yBAAyB,CAAC,KAAK,EAAE,gBAAgB,GAAG,OAAO,CAE1E"}
+{"version":3,"file":"python.d.ts","sourceRoot":"","sources":["../../../src/snippets/python.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AACpD,OAAO,KAAK,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,MAAM,mBAAmB,CAAC;AAG1F,OAAO,KAAK,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAErE,eAAO,MAAM,qBAAqB,UAC1B,gBAAgB,eACV,MAAM,SACZ;IACN,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,QAAQ,CAAC,EAAE,0BAA0B,EAAE,CAAC;IACxC,WAAW,CAAC,EAAE,oBAAoB,CAAC,aAAa,CAAC,CAAC;IAClD,UAAU,CAAC,EAAE,oBAAoB,CAAC,YAAY,CAAC,CAAC;IAChD,KAAK,CAAC,EAAE,oBAAoB,CAAC,OAAO,CAAC,CAAC;CACtC,KACC,gBAAgB,EAwGlB,CAAC;AAEF,eAAO,MAAM,6BAA6B,UAAW,gBAAgB,KAAG,gBAStE,CAAC;AAEH,eAAO,MAAM,kCAAkC,UAAW,gBAAgB,KAAG,gBAe3E,CAAC;AAEH,eAAO,MAAM,YAAY,UAAW,gBAAgB,KAAG,gBAQrD,CAAC;AAEH,eAAO,MAAM,WAAW,UAAW,gBAAgB,KAAG,gBAQpD,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,KAAG,gBAW3D,CAAC;AAEH,eAAO,MAAM,cAAc,UAAW,gBAAgB,KAAG,gBAOvD,CAAC;AAEH,eAAO,MAAM,kBAAkB,UAAW,gBAAgB,KAAG,gBA+B5D,CAAC;AAEF,eAAO,MAAM,gCAAgC,UAAW,gBAAgB,KAAG,gBAWzE,CAAC;AAEH,eAAO,MAAM,cAAc,EAAE,OAAO,CACnC,MAAM,CACL,YAAY,EACZ,CACC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,EACnB,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAC1B,gBAAgB,GAAG,gBAAgB,EAAE,CAC1C,CA8BD,CAAC;AAEF,wBAAgB,yBAAyB,CACxC,KAAK,EAAE,gBAAgB,EACvB,WAAW,EAAE,MAAM,EACnB,IAAI,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAC5B,gBAAgB,GAAG,gBAAgB,EAAE,CAwBvC;AAED,wBAAgB,yBAAyB,CAAC,KAAK,EAAE,gBAAgB,GAAG,OAAO,CAE1E"}

package/dist/src/tasks/image-segmentation/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-segmentation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cA+Ff,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-segmentation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cA8Ff,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/src/tasks/object-detection/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/object-detection/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAkFf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/object-detection/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAiFf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/src/tasks/text-to-speech/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-speech/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAyEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-speech/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cA0Ef,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.12.26",
+  "version": "0.12.28",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/model-libraries.ts

@@ -373,6 +373,12 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
 		repoUrl: "https://github.com/abetlen/llama-cpp-python",
 		snippets: snippets.llama_cpp_python,
 	},
+	"mini-omni2": {
+		prettyLabel: "Mini-Omni2",
+		repoName: "Mini-Omni2",
+		repoUrl: "https://github.com/gpt-omni/mini-omni2",
+		countDownloads: `path:"model_config.yaml"`,
+	},
 	mindspore: {
 		prettyLabel: "MindSpore",
 		repoName: "mindspore",

package/src/pipelines.ts

@@ -1,4 +1,4 @@
-export const MODALITIES = ["cv", "nlp", "audio", "tabular", "multimodal", "rl", "other"] as const;
+export const MODALITIES = ["multimodal", "nlp", "cv", "audio", "tabular", "rl", "other"] as const;
 
 export type Modality = (typeof MODALITIES)[number];
 

package/src/snippets/curl.ts

@@ -26,9 +26,8 @@ export const snippetTextGeneration = (
 	if (model.tags.includes("conversational")) {
 		// Conversational model detected, so we display a code snippet that features the Messages API
 		const streaming = opts?.streaming ?? true;
-		const messages: ChatCompletionInputMessage[] = opts?.messages ?? [
-			{ role: "user", content: "What is the capital of France?" },
-		];
+		const exampleMessages = getModelInputSnippet(model) as ChatCompletionInputMessage[];
+		const messages = opts?.messages ?? exampleMessages;
 
 		const config = {
 			...(opts?.temperature ? { temperature: opts.temperature } : undefined),
@@ -63,34 +62,6 @@ export const snippetTextGeneration = (
 	}
 };
 
-export const snippetImageTextToTextGeneration = (model: ModelDataMinimal, accessToken: string): InferenceSnippet => {
-	if (model.tags.includes("conversational")) {
-		// Conversational model detected, so we display a code snippet that features the Messages API
-		return {
-			content: `curl 'https://api-inference.huggingface.co/models/${model.id}/v1/chat/completions' \\
--H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}" \\
--H 'Content-Type: application/json' \\
--d '{
-	"model": "${model.id}",
-	"messages": [
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"}},
-				{"type": "text", "text": "Describe this image in one sentence."}
-			]
-		}
-	],
-	"max_tokens": 500,
-	"stream": false
-}'
-`,
-		};
-	} else {
-		return snippetBasic(model, accessToken);
-	}
-};
-
 export const snippetZeroShotClassification = (model: ModelDataMinimal, accessToken: string): InferenceSnippet => ({
 	content: `curl https://api-inference.huggingface.co/models/${model.id} \\
 	-X POST \\
@@ -122,7 +93,7 @@ export const curlSnippets: Partial<
 	summarization: snippetBasic,
 	"feature-extraction": snippetBasic,
 	"text-generation": snippetTextGeneration,
-	"image-text-to-text": snippetImageTextToTextGeneration,
+	"image-text-to-text": snippetTextGeneration,
 	"text2text-generation": snippetBasic,
 	"fill-mask": snippetBasic,
 	"sentence-similarity": snippetBasic,

package/src/snippets/inputs.ts

@@ -1,4 +1,5 @@
 import type { PipelineType } from "../pipelines";
+import type { ChatCompletionInputMessage } from "../tasks";
 import type { ModelDataMinimal } from "./types";
 
 const inputsZeroShotClassification = () =>
@@ -40,7 +41,30 @@ const inputsTextClassification = () => `"I like you. I love you"`;
 
 const inputsTokenClassification = () => `"My name is Sarah Jessica Parker but you can call me Jessica"`;
 
-const inputsTextGeneration = () => `"Can you please let us know more details about your "`;
+const inputsTextGeneration = (model: ModelDataMinimal): string | ChatCompletionInputMessage[] => {
+	if (model.tags.includes("conversational")) {
+		return model.pipeline_tag === "text-generation"
+			? [{ role: "user", content: "What is the capital of France?" }]
+			: [
+					{
+						role: "user",
+						content: [
+							{
+								type: "text",
+								text: "Describe this image in one sentence.",
+							},
+							{
+								type: "image_url",
+								image_url: {
+									url: "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg",
+								},
+							},
+						],
+					},
+			  ];
+	}
+	return `"Can you please let us know more details about your "`;
+};
 
 const inputsText2TextGeneration = () => `"The answer to the universe is"`;
 
@@ -84,7 +108,7 @@ const inputsTabularPrediction = () =>
 const inputsZeroShotImageClassification = () => `"cats.jpg"`;
 
 const modelInputSnippets: {
-	[key in PipelineType]?: (model: ModelDataMinimal) => string;
+	[key in PipelineType]?: (model: ModelDataMinimal) => string | ChatCompletionInputMessage[];
 } = {
 	"audio-to-audio": inputsAudioToAudio,
 	"audio-classification": inputsAudioClassification,
@@ -116,18 +140,24 @@ const modelInputSnippets: {
 
 // Use noWrap to put the whole snippet on a single line (removing new lines and tabulations)
 // Use noQuotes to strip quotes from start & end (example: "abc" -> abc)
-export function getModelInputSnippet(model: ModelDataMinimal, noWrap = false, noQuotes = false): string {
+export function getModelInputSnippet(
+	model: ModelDataMinimal,
+	noWrap = false,
+	noQuotes = false
+): string | ChatCompletionInputMessage[] {
 	if (model.pipeline_tag) {
 		const inputs = modelInputSnippets[model.pipeline_tag];
 		if (inputs) {
 			let result = inputs(model);
-			if (noWrap) {
-				result = result.replace(/(?:(?:\r?\n|\r)\t*)|\t+/g, " ");
-			}
-			if (noQuotes) {
-				const REGEX_QUOTES = /^"(.+)"$/s;
-				const match = result.match(REGEX_QUOTES);
-				result = match ? match[1] : result;
+			if (typeof result === "string") {
+				if (noWrap) {
+					result = result.replace(/(?:(?:\r?\n|\r)\t*)|\t+/g, " ");
+				}
+				if (noQuotes) {
+					const REGEX_QUOTES = /^"(.+)"$/s;
+					const match = result.match(REGEX_QUOTES);
+					result = match ? match[1] : result;
+				}
 			}
 			return result;
 		}

package/src/snippets/js.ts

@@ -40,9 +40,8 @@ export const snippetTextGeneration = (
 	if (model.tags.includes("conversational")) {
 		// Conversational model detected, so we display a code snippet that features the Messages API
 		const streaming = opts?.streaming ?? true;
-		const messages: ChatCompletionInputMessage[] = opts?.messages ?? [
-			{ role: "user", content: "What is the capital of France?" },
-		];
+		const exampleMessages = getModelInputSnippet(model) as ChatCompletionInputMessage[];
+		const messages = opts?.messages ?? exampleMessages;
 		const messagesStr = stringifyMessages(messages, { sep: ",\n\t\t", start: "[\n\t\t", end: "\n\t]" });
 
 		const config = {
@@ -148,36 +147,6 @@ console.log(chatCompletion.choices[0].message);`,
 	}
 };
 
-export const snippetImageTextToTextGeneration = (model: ModelDataMinimal, accessToken: string): InferenceSnippet => {
-	if (model.tags.includes("conversational")) {
-		// Conversational model detected, so we display a code snippet that features the Messages API
-		return {
-			content: `import { HfInference } from "@huggingface/inference";
-
-const inference = new HfInference("${accessToken || `{API_TOKEN}`}");
-const imageUrl = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg";
-
-for await (const chunk of inference.chatCompletionStream({
-	model: "${model.id}",
-	messages: [
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": imageUrl}},
-				{"type": "text", "text": "Describe this image in one sentence."},
-			],
-		}
-	],
-	max_tokens: 500,
-})) {
-	process.stdout.write(chunk.choices[0]?.delta?.content || "");
-}`,
-		};
-	} else {
-		return snippetBasic(model, accessToken);
-	}
-};
-
 export const snippetZeroShotClassification = (model: ModelDataMinimal, accessToken: string): InferenceSnippet => ({
 	content: `async function query(data) {
 	const response = await fetch(
@@ -307,7 +276,7 @@ export const jsSnippets: Partial<
 	summarization: snippetBasic,
 	"feature-extraction": snippetBasic,
 	"text-generation": snippetTextGeneration,
-	"image-text-to-text": snippetImageTextToTextGeneration,
+	"image-text-to-text": snippetTextGeneration,
 	"text2text-generation": snippetBasic,
 	"fill-mask": snippetBasic,
 	"sentence-similarity": snippetBasic,

package/src/snippets/python.ts

@@ -16,9 +16,8 @@ export const snippetConversational = (
 	}
 ): InferenceSnippet[] => {
 	const streaming = opts?.streaming ?? true;
-	const messages: ChatCompletionInputMessage[] = opts?.messages ?? [
-		{ role: "user", content: "What is the capital of France?" },
-	];
+	const exampleMessages = getModelInputSnippet(model) as ChatCompletionInputMessage[];
+	const messages = opts?.messages ?? exampleMessages;
 	const messagesStr = stringifyMessages(messages, {
 		sep: ",\n\t",
 		start: `[\n\t`,
@@ -121,30 +120,6 @@ print(completion.choices[0].message)`,
 	}
 };
 
-export const snippetConversationalWithImage = (model: ModelDataMinimal, accessToken: string): InferenceSnippet => ({
-	content: `from huggingface_hub import InferenceClient
-
-client = InferenceClient(api_key="${accessToken || "{API_TOKEN}"}")
-
-image_url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
-
-for message in client.chat_completion(
-	model="${model.id}",
-	messages=[
-		{
-			"role": "user",
-			"content": [
-				{"type": "image_url", "image_url": {"url": image_url}},
-				{"type": "text", "text": "Describe this image in one sentence."},
-			],
-		}
-	],
-	max_tokens=500,
-	stream=True,
-):
-	print(message.choices[0].delta.content, end="")`,
-});
-
 export const snippetZeroShotClassification = (model: ModelDataMinimal): InferenceSnippet => ({
 	content: `def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
@@ -282,7 +257,7 @@ export const pythonSnippets: Partial<
 	"feature-extraction": snippetBasic,
 	"text-generation": snippetBasic,
 	"text2text-generation": snippetBasic,
-	"image-text-to-text": snippetConversationalWithImage,
+	"image-text-to-text": snippetConversational,
 	"fill-mask": snippetBasic,
 	"sentence-similarity": snippetBasic,
 	"automatic-speech-recognition": snippetFile,
@@ -306,12 +281,9 @@ export function getPythonInferenceSnippet(
 	accessToken: string,
 	opts?: Record<string, unknown>
 ): InferenceSnippet | InferenceSnippet[] {
-	if (model.pipeline_tag === "text-generation" && model.tags.includes("conversational")) {
+	if (model.tags.includes("conversational")) {
 		// Conversational model detected, so we display a code snippet that features the Messages API
 		return snippetConversational(model, accessToken, opts);
-	} else if (model.pipeline_tag === "image-text-to-text" && model.tags.includes("conversational")) {
-		// Example sending an image to the Message API
-		return snippetConversationalWithImage(model, accessToken);
 	} else {
 		let snippets =
 			model.pipeline_tag && model.pipeline_tag in pythonSnippets

package/src/tasks/image-segmentation/data.ts

@@ -44,8 +44,7 @@ const taskData: TaskDataCustom = {
 	models: [
 		{
 			// TO DO: write description
-			description:
-				"Solid semantic segmentation model trained on ADE20k.",
+			description: "Solid semantic segmentation model trained on ADE20k.",
 			id: "openmmlab/upernet-convnext-small",
 		},
 		{

package/src/tasks/object-detection/data.ts

@@ -51,8 +51,7 @@ const taskData: TaskDataCustom = {
 			id: "jameslahm/yolov10x",
 		},
 		{
-			description:
-				"Fast and accurate object detection model trained on COCO and Object365 datasets.",
+			description: "Fast and accurate object detection model trained on COCO and Object365 datasets.",
 			id: "PekingU/rtdetr_r18vd_coco_o365",
 		},
 	],

package/src/tasks/text-to-speech/data.ts

@@ -57,7 +57,8 @@ const taskData: TaskDataCustom = {
 			id: "suno/bark",
 		},
 		{
-			description: "An application on XTTS, a voice generation model that lets you clone voices into different languages.",
+			description:
+				"An application on XTTS, a voice generation model that lets you clone voices into different languages.",
 			id: "coqui/xtts",
 		},
 		{