Add support for Helium and Glm

[xenova]

Made possible by huggingface/optimum#2162.

Example: Text-generation w/ onnx-community/helium-1-preview-2b-ONNX

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/helium-1-preview-2b-ONNX",
  { dtype: "q4" },
);

// Define the prompt
const text = "Hello, today is a great day to";

// Generate a response
const output = await generator(text, { max_new_tokens: 128 });
console.log(output[0].generated_text);

Example: Text-generation w/ onnx-community/glm-edge-1.5b-chat-ONNX

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/glm-edge-1.5b-chat-ONNX",
  { dtype: "q4" },
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Tell me a joke." },
];

// Generate a response
const output = await generator(messages, { max_new_tokens: 128 });
console.log(output[0].generated_text.at(-1).content);
// "Why don't scientists trust atoms?\n\nBecause they make up everything!"