gliner2.5-multi-onnx

beshkenadze/gliner2.5-multi-onnx

gliner2.5-multi-onnx is a machine learning model from beshkenadze. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for onnx. The card lists the license as apache-2.0.

ONNX export of fastino/gliner2.5-multi-v1 (GLiNER2, boundary architecture, mDeBERTa-v3-base, Apache 2.0) split into the two graphs that form-pilot runs with onnxruntime-web to turn résumés and other documents into Lab…

Downloads · 30 days

Access

Public

Updated Sep 20, 2026

Repo size

577 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.onnx561 MB · 97%

At a glance

Library: onnx
License: apache-2.0
Access: Public
Created: Sep 20, 2026
Updated: Sep 20, 2026
SHA: 8f625de9

Base models

fastino/gliner2.5-multi-v1

Model card

From the Hugging Face model README

GLiNER2.5-multi, ONNX export for the browser

File	Size	What
`encoder_fp16.onnx`	556 MB	mDeBERTa-v3-base encoder, weights in fp16, `float32` output. Inputs `input_ids`, `attention_mask` (int64, `[1, seq]`), output `last_hidden_state` (`[1, seq, 768]`).
`head.onnx`	5 MB	Boundary head. Inputs `text_states` `[1, W, 768]`, `text_mask` (bool `[1, W]`), `query_states` `[1, Q, 768]`, `query_mask` (bool `[1, Q]`); outputs `indices` `[1, Q, C, 2]` (int64 word spans, end exclusive), `valid_mask` `[1, Q, C]`, `pair_logits` `[1, Q, C]`.
`tokenizer.json`, `tokenizer_config.json`	16 MB	Unchanged from the base model; the schema marker tokens (`[P]`, `[C]`, `[SEP_TEXT]`, `[DESCRIPTION]`, …) are already registered.

Usage

The pre- and post-processing (word splitting, schema prompt layout, routing indices, span decoding) is a port of gliner2's SchemaTransformer and lives in packages/extract of form-pilot. In short: encode ( [P] prompt ( [C] field … ) ) [SEP_TEXT] words… token by token, gather last_hidden_state at each text word's first subword and at each [C] marker, run the head, take the argmax over pair_logits where valid_mask is set.

Run the encoder on WebGPU (≈200 ms per 300-token chunk on an Apple M-series GPU) or WASM (≈2 s single-threaded); run the head on WASM, it returns wrong results on the WebGPU execution provider of onnxruntime-web 1.22–1.30. Keep chunks at ~120 words: the boundary model is not meant for whole documents at once.

How it was exported

Encoder: torch.onnx.export (opset 17, legacy exporter) of the encoder converted with .half(), output cast to float32. Post-hoc fp16 converters broke DeBERTa's Cast/If nodes.
Head: torch.onnx.export(dynamo=True) of BoundaryHead.forward(..., return_candidates=True) returning candidates.indices / valid_mask / pair_logits, with torch.sort and torch.argsort patched to drop stable=True (no ONNX function for the stable overload); external data embedded into the single file.
Verified against PyTorch on a synthetic résumé: identical best spans, probabilities within 0.01 in fp16.

Not quantized on purpose: int8 dynamic quantization lowered confidences on low-margin fields.

Library: onnx
License: apache-2.0
Languages: multilingual
Created: Sep 20, 2026
Updated: Sep 20, 2026