ONNX Model Zoo

onnx-community/ERNIE-4.5-0.3B-ONNX

By onnx-community · ↓ 8 · ♥ 3 · Updated 2025-11-30

What's in this repo

This page lists the files in onnx-community/ERNIE-4.5-0.3B-ONNX, including model.onnx, model_bnb4.onnx, model_fp16.onnx and more.

  • 8 ONNX models (.onnx files)
  • 26 files, including 8 .onnx, 8 .onnx_data, 6 .json, 1 .md, 1 .jinja, 1 .model
  • Last updated 2025-11-30

ONNX files

File Size Download
onnx/model.onnx — Download
onnx/model_bnb4.onnx — Download
onnx/model_fp16.onnx — Download
onnx/model_int8.onnx — Download
onnx/model_q4.onnx — Download
onnx/model_q4f16.onnx — Download
onnx/model_quantized.onnx — Download
onnx/model_uint8.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT 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 generate text as follows:

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/ERNIE-4.5-0.3B-ONNX",
  { dtype: "fp32" }, // Options: "fp32", "fp16", "q8", "q4", "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);
// The capital of France is Paris.

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 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Model info

text-generation transformers.js
transformers.js onnx ernie4_5 text-generation conversational base_model:baidu/ERNIE-4.5-0.3B-PT base_model:quantized:baidu/ERNIE-4.5-0.3B-PT region:us
↓ 8 ♥ 3

Created: 2025-07-04

Updated: 2025-11-30

View on Hugging Face

Files (26)

.gitattributes
README.md
added_tokens.json
chat_template.jinja
config.json
generation_config.json
onnx/model.onnx ONNX
onnx/model.onnx_data
onnx/model_bnb4.onnx ONNX
onnx/model_bnb4.onnx_data
onnx/model_fp16.onnx ONNX
onnx/model_fp16.onnx_data
onnx/model_int8.onnx ONNX
onnx/model_int8.onnx_data
onnx/model_q4.onnx ONNX
onnx/model_q4.onnx_data
onnx/model_q4f16.onnx ONNX
onnx/model_q4f16.onnx_data
onnx/model_quantized.onnx ONNX
onnx/model_quantized.onnx_data
onnx/model_uint8.onnx ONNX
onnx/model_uint8.onnx_data
special_tokens_map.json
tokenizer.json
tokenizer.model
tokenizer_config.json

Related models