LFM2.5-Encoder-350M-ONNX

ONNX export of LiquidAI/LFM2.5-Encoder-350M, quantized to run fully in the browser through transformers.js. No inference server: the weights are fetched once, cached, and every forward pass happens in the tab.

The base bidirectional encoder with its tied masked-LM head. Outputs vocabulary logits and the final hidden states, so it doubles as a sentence-embedding backbone.

All credit for the model itself goes to Liquid AI. This repository contains only a re-export; the weights are unchanged apart from quantization, and the original LFM Open License v1.0 applies.

Try it in your browser → — no install, no API key.

Tooling, demo and the export pipeline: https://github.com/kucukkanat/lfm-encoders

Files

The graph takes input_ids + attention_mask, is dynamic in batch and sequence, and returns logits and last_hidden_state.

Usage

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

const id = "kucukkanat/LFM2.5-Encoder-350M-ONNX";
const tokenizer = await AutoTokenizer.from_pretrained(id);
const model = await PreTrainedModel.from_pretrained(id, { dtype: "q8" });

const { input_ids } = tokenizer("some text");
const out = await model({
  input_ids,
  attention_mask: new Tensor("int64", new BigInt64Array(input_ids.dims[1]).fill(1n), input_ids.dims),
});

PreTrainedModel rather than AutoModel is deliberate: this is a plain "feed the named inputs, read the named outputs" session, not one of transformers.js's built-in architectures.

Accuracy

Measured from JavaScript against the fp32 PyTorch reference. Δ is the largest absolute difference in a final probability.

Notes

• q8 is smaller on disk but uses more browser RAM than fp32 and runs slower: onnxruntime's WASM kernels compute in float, so quantized weights are unpacked at session load. Quantization here buys download size, not speed or memory.
• Budget roughly 1.5 GB of RAM per resident model, and expect a tab to hold its high-water mark until reloaded.
• fp16 / q4f16 are deliberately absent: RMSNorm's variance overflows fp16 on this architecture and every hidden state collapses to zeros.