https://huggingface.co/oxyapi/oxy-1-micro with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then use the model to generate text like this:

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/oxy-1-micro",
  { dtype: "q4" },
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a wise old wizard in a mystical land. A traveler approaches you seeking advice." },
  { role: "user", content: "Where is the nearest inn?" },
];

// Generate a response
const output = await generator(messages, { max_new_tokens: 256, do_sample: false });
console.log(output[0].generated_text.at(-1).content);
See example output
Greetings, traveler! I am here to guide you through this enchanted realm. The nearest inn is located not far from my humble abode. It is called "The Quiet Haven," and it is nestled on a quiet path just beyond my property. You can find it by following the winding paths of the forest. May I assist you further?

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using ๐Ÿค— Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Downloads last month
31
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for onnx-community/oxy-1-micro

Base model

Qwen/Qwen2-1.5B
Finetuned
oxyapi/oxy-1-micro
Quantized
(10)
this model