Merge branch 'main' into node-llama-cpp-option

Author: Vaibhavs10

README.md

@@ -27,20 +27,24 @@ await uploadFile({
   }
 });
 
-// Use hosted inference
-
-await inference.translation({
-  model: 't5-base',
-  inputs: 'My name is Wolfgang and I live in Berlin'
-})
+// Use Inference API
+
+await inference.chatCompletion({
+  model: "meta-llama/Llama-3.1-8B-Instruct",
+  messages: [
+    {
+      role: "user",
+      content: "Hello, nice to meet you!",
+    },
+  ],
+  max_tokens: 512,
+  temperature: 0.5,
+});
 
 await inference.textToImage({
-  model: 'stabilityai/stable-diffusion-2',
-  inputs: 'award winning high resolution photo of a giant tortoise/((ladybird)) hybrid, [trending on artstation]',
-  parameters: {
-    negative_prompt: 'blurry',
-  }
-})
+  model: "black-forest-labs/FLUX.1-dev",
+  inputs: "a picture of a green bird",
+});
 
 // and much more…
 ```
@@ -123,33 +127,33 @@ const inference = new HfInference(HF_TOKEN);
 
 // Chat completion API
 const out = await inference.chatCompletion({
-  model: "mistralai/Mistral-7B-Instruct-v0.2",
-  messages: [{ role: "user", content: "Complete the this sentence with words one plus one is equal " }],
-  max_tokens: 100
+  model: "meta-llama/Llama-3.1-8B-Instruct",
+  messages: [{ role: "user", content: "Hello, nice to meet you!" }],
+  max_tokens: 512
 });
 console.log(out.choices[0].message);
 
 // Streaming chat completion API
 for await (const chunk of inference.chatCompletionStream({
-  model: "mistralai/Mistral-7B-Instruct-v0.2",
-  messages: [{ role: "user", content: "Complete the this sentence with words one plus one is equal " }],
-  max_tokens: 100
+  model: "meta-llama/Llama-3.1-8B-Instruct",
+  messages: [{ role: "user", content: "Hello, nice to meet you!" }],
+  max_tokens: 512
 })) {
   console.log(chunk.choices[0].delta.content);
 }
 
 // You can also omit "model" to use the recommended model for the task
 await inference.translation({
-  model: 't5-base',
-  inputs: 'My name is Wolfgang and I live in Amsterdam'
-})
+  inputs: "My name is Wolfgang and I live in Amsterdam",
+  parameters: {
+    src_lang: "en",
+    tgt_lang: "fr",
+  },
+});
 
 await inference.textToImage({
-  model: 'stabilityai/stable-diffusion-2',
-  inputs: 'award winning high resolution photo of a giant tortoise/((ladybird)) hybrid, [trending on artstation]',
-  parameters: {
-    negative_prompt: 'blurry',
-  }
+  model: 'black-forest-labs/FLUX.1-dev',
+  inputs: 'a picture of a green bird',
 })
 
 await inference.imageToText({
@@ -162,13 +166,13 @@ const gpt2 = inference.endpoint('https://xyz.eu-west-1.aws.endpoints.huggingface
 const { generated_text } = await gpt2.textGeneration({inputs: 'The answer to the universe is'});
 
 //Chat Completion
-const mistal = inference.endpoint(
- "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2"
+const llamaEndpoint = inference.endpoint(
+ "https://api-inference.huggingface.co/models/meta-llama/Llama-3.1-8B-Instruct"
 );
-const out = await mistal.chatCompletion({
- model: "mistralai/Mistral-7B-Instruct-v0.2",
- messages: [{ role: "user", content: "Complete the this sentence with words one plus one is equal " }],
- max_tokens: 100,
+const out = await llamaEndpoint.chatCompletion({
+ model: "meta-llama/Llama-3.1-8B-Instruct",
+ messages: [{ role: "user", content: "Hello, nice to meet you!" }],
+ max_tokens: 512,
 });
 console.log(out.choices[0].message);
 ```

packages/inference/README.md

@@ -91,23 +91,21 @@ Using the `chatCompletion` method, you can generate text with models compatible
 ```typescript
 // Non-streaming API
 const out = await hf.chatCompletion({
-  model: "mistralai/Mistral-7B-Instruct-v0.2",
-  messages: [{ role: "user", content: "Complete the this sentence with words one plus one is equal " }],
-  max_tokens: 500,
+  model: "meta-llama/Llama-3.1-8B-Instruct",
+  messages: [{ role: "user", content: "Hello, nice to meet you!" }],
+  max_tokens: 512,
   temperature: 0.1,
-  seed: 0,
 });
 
 // Streaming API
 let out = "";
 for await (const chunk of hf.chatCompletionStream({
-  model: "mistralai/Mistral-7B-Instruct-v0.2",
+  model: "meta-llama/Llama-3.1-8B-Instruct",
   messages: [
-    { role: "user", content: "Complete the equation 1+1= ,just the answer" },
+    { role: "user", content: "Can you help me solve an equation?" },
   ],
-  max_tokens: 500,
+  max_tokens: 512,
   temperature: 0.1,
-  seed: 0,
 })) {
   if (chunk.choices && chunk.choices.length > 0) {
     out += chunk.choices[0].delta.content;
@@ -396,11 +394,8 @@ Creates an image from a text prompt.
 
 ```typescript
 await hf.textToImage({
-  inputs: 'award winning high resolution photo of a giant tortoise/((ladybird)) hybrid, [trending on artstation]',
-  model: 'stabilityai/stable-diffusion-2',
-  parameters: {
-    negative_prompt: 'blurry',
-  }
+  model: 'black-forest-labs/FLUX.1-dev',
+  inputs: 'a picture of a green bird'
 })
 ```
 
@@ -583,7 +578,7 @@ const { generated_text } = await gpt2.textGeneration({inputs: 'The answer to the
 
 // Chat Completion Example
 const ep = hf.endpoint(
-  "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2"
+  "https://api-inference.huggingface.co/models/meta-llama/Llama-3.1-8B-Instruct"
 );
 const stream = ep.chatCompletionStream({
   model: "tgi",

packages/tasks/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "@huggingface/tasks",
 	"packageManager": "[email protected]",
-	"version": "0.12.17",
+	"version": "0.12.20",
 	"description": "List of ML tasks for huggingface.co/tasks",
 	"repository": "https://github.com/huggingface/huggingface.js.git",
 	"publishConfig": {

packages/tasks/src/local-apps.ts

@@ -162,8 +162,8 @@ const snippetLocalAI = (model: ModelData, filepath?: string): LocalAppSnippet[]
 const snippetVllm = (model: ModelData): LocalAppSnippet[] => {
 	const runCommand = [
 		"# Call the server using curl:",
-		`curl -X POST "http://localhost:8000/v1/chat/completions" \\ `,
-		`	-H "Content-Type: application/json" \\ `,
+		`curl -X POST "http://localhost:8000/v1/chat/completions" \\`,
+		`	-H "Content-Type: application/json" \\`,
 		`	--data '{`,
 		`		"model": "${model.id}",`,
 		`		"messages": [`,
@@ -229,12 +229,13 @@ export const LOCAL_APPS = {
 		docsUrl: "https://docs.vllm.ai",
 		mainTask: "text-generation",
 		displayOnModelPage: (model: ModelData) =>
-			isAwqModel(model) ||
-			isGptqModel(model) ||
-			isAqlmModel(model) ||
-			isMarlinModel(model) ||
-			isLlamaCppGgufModel(model) ||
-			isTransformersModel(model),
+			(isAwqModel(model) ||
+				isGptqModel(model) ||
+				isAqlmModel(model) ||
+				isMarlinModel(model) ||
+				isLlamaCppGgufModel(model) ||
+				isTransformersModel(model)) &&
+			(model.pipeline_tag === "text-generation" || model.pipeline_tag === "image-text-to-text"),
 		snippet: snippetVllm,
 	},
 	lmstudio: {

packages/tasks/src/model-libraries.ts

@@ -516,6 +516,12 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
 		filter: false,
 		countDownloads: `path:"model.safetensors"`,
 	},
+	reverb: {
+		prettyLabel: "Reverb",
+		repoName: "Reverb",
+		repoUrl: "https://github.com/revdotcom/reverb",
+		filter: false,
+	},
 	saelens: {
 		prettyLabel: "SAELens",
 		repoName: "SAELens",

packages/tasks/src/tasks/image-text-to-text/data.ts

@@ -43,8 +43,8 @@ const taskData: TaskDataCustom = {
 	metrics: [],
 	models: [
 		{
-			description: "Cutting-edge vision language model that can take multiple image inputs.",
-			id: "facebook/chameleon-7b",
+			description: "Powerful vision language model with great visual understanding and reasoning capabilities.",
+			id: "meta-llama/Llama-3.2-11B-Vision-Instruct",
 		},
 		{
 			description: "Cutting-edge conversational vision language model that can take multiple image inputs.",