Add support for qwen3_5_text <-> Qwen3_5ForCausalLM

[xenova]

So you can load and run qwen3_5 models that only have the text component. e.g.,

import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/Qwen3.5-0.8B-Text-ONNX",
  { device: "webgpu", dtype: "q4f16" },
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What is the capital of France?" },
];

// Generate a response
const output = await generator(messages, {
  max_new_tokens: 512,
  do_sample: false,
  streamer: new TextStreamer(generator.tokenizer, {
    skip_prompt: true,
    skip_special_tokens: true,
  }),
});
console.log(output[0].generated_text.at(-1).content);

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.