NeoBERT-ONNX

npm i @huggingface/transformers

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

// Create feature extraction pipeline
const extractor = await pipeline("feature-extraction", "onnx-community/NeoBERT-ONNX");

// Compute embeddings
const text = "NeoBERT is the most efficient model of its kind!";
const embedding = await extractor(text, { pooling: "cls" });
console.log(embedding.dims); // [1, 768]

import { AutoModel, AutoTokenizer } from "@huggingface/transformers";

// Load model and tokenizer
const model_id = "onnx-community/NeoBERT-ONNX";
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const model = await AutoModel.from_pretrained(model_id);

// Tokenize input text
const text = "NeoBERT is the most efficient model of its kind!";
const inputs = tokenizer(text);

// Generate embeddings
const outputs = await model(inputs);
const embedding = outputs.last_hidden_state.slice(null, 0);
console.log(embedding.dims); // [1, 768]

from transformers import AutoTokenizer
from huggingface_hub import hf_hub_download
import onnxruntime as ort

model_id = "onnx-community/NeoBERT-ONNX"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model_file = hf_hub_download(model_id, filename="onnx/model.onnx")
session = ort.InferenceSession(model_file)

text = ["NeoBERT is the most efficient model of its kind!"]
inputs = tokenizer(text, return_tensors="np").data
outputs = session.run(None, inputs)[0]
embeddings = outputs[:, 0, :]
print(f"{embeddings.shape=}") # (1, 768)