Update README.md

README.md

@@ -112,7 +112,10 @@ If you haven't already, you can install the [Transformers.js](https://huggingfac
 npm i @huggingface/transformers
 ```
 
-You can then generate text as follows:
+
+
+**Example**: Basic example
+
 ```js
 import { pipeline, TextStreamer } from "@huggingface/transformers";
 
@@ -133,12 +136,77 @@ const messages = [
 const output = await generator(messages, {
     max_new_tokens: 512,
     do_sample: false,
-    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true}),
+    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true }),
 });
 console.log(output[0].generated_text.at(-1).content);
 // The capital of France is Paris.
 ```
 
+
+**Example**: Tool calling
+
+```js
+import { AutoModelForCausalLM, AutoTokenizer, TextStreamer } from "@huggingface/transformers";
+
+// Load tokenizer and model
+const model_id = "onnx-community/LFM2-700M-ONNX";
+const tokenizer = await AutoTokenizer.from_pretrained(model_id);
+const model = await AutoModelForCausalLM.from_pretrained(
+  model_id, { dtype: "q4", device: "webgpu" },
+);
+
+// Define tools and messages
+const tools = [
+  {
+    name: "get_weather",
+    description: "Get current weather information for a location",
+    parameters: {
+      type: "object",
+      properties: {
+        location: {
+          type: "string",
+          description: "The city and state, e.g. San Francisco, CA",
+        },
+        unit: {
+          type: "string",
+          enum: ["celsius", "fahrenheit"],
+          description: "The unit of temperature to use",
+        },
+      },
+      required: ["location"],
+    },
+  },
+];
+const messages = [
+  {
+    role: "user",
+    content: "What's the weather like in New York?"
+  },
+];
+
+// Prepare inputs
+const input = tokenizer.apply_chat_template(messages, {
+  tools,
+  add_generation_prompt: true,
+  return_dict: true,
+});
+
+// Generate output
+const sequences = await model.generate({
+  ...input,
+  max_new_tokens: 512,
+  do_sample: false,
+  streamer: new TextStreamer(tokenizer, { skip_prompt: true, skip_special_tokens: false }),
+});
+
+// Decode and print the generated text
+const response = tokenizer.batch_decode(
+  sequences.slice(null, [input.input_ids.dims[1], null]),
+  { skip_special_tokens: true },
+);
+console.log(response[0]); // [get_weather(location="New York", unit="fahrenheit")]
+```
+
 ### ONNXRuntime
 
 ```py