Update README.md

README.md

@@ -134,7 +134,7 @@ 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.
@@ -150,9 +150,10 @@ import { AutoModelForCausalLM, AutoTokenizer, TextStreamer } from "@huggingface/
 const model_id = "onnx-community/LFM2-1.2B-ONNX";
 const tokenizer = await AutoTokenizer.from_pretrained(model_id);
 const model = await AutoModelForCausalLM.from_pretrained(
-  model_id, { dtype: "q4f16", device: "webgpu" },
+  model_id, { dtype: "q4", device: "webgpu" },
 );
 
+// Define tools and messages
 const tools = [
   {
     name: "get_weather",
@@ -181,25 +182,19 @@ const messages = [
   },
 ];
 
-// Tokenize input
+// Prepare inputs
 const input = tokenizer.apply_chat_template(messages, {
   tools,
   add_generation_prompt: true,
   return_dict: true,
 });
 
-// Set up the streamer
-const streamer = new TextStreamer(tokenizer, {
-  skip_prompt: true,
-  skip_special_tokens: false,
-});
-
 // Generate output
 const sequences = await model.generate({
   ...input,
   max_new_tokens: 512,
   do_sample: false,
-  streamer,
+  streamer: new TextStreamer(tokenizer, { skip_prompt: true, skip_special_tokens: false }),
 });
 
 // Decode and print the generated text