onnx-community/gliner2-multi-v1-agent-ONNX

GLiNER2 multi v1, one-graph ONNX for the browser

ONNX export of fastino/gliner2-multi-v1 (mDeBERTa-v3-base, multilingual) as a single graph that serves both entity extraction and label classification, for Transformers.js on WebGPU. It was made for Zipline, a browser agent that runs entirely in Chrome, and covers the two calls such an agent makes: pulling values out of a goal (extract_entities) and scoring page controls against it (classify with a softmax over labels).

file	size
onnx/model_fp16.onnx + _data	614 MB (WebGPU)
onnx/model.onnx + _data	1.23 GB (fp32, reference)

Inputs and outputs

name	shape	meaning
input_ids, attention_mask	[1, seq]	the GLiNER2 processor's prompt: ( [P] task [DESCRIPTION] label: desc … ( [E]/[L] label … ) ) [SEP_TEXT] words
word_positions	[1, words]	index of the first sub-token of each text word
schema_positions	[1, 1 + labels]	index of [P], then of each [E] (extraction) or [L] (classification) marker
cls_logits	[1, labels]	classifier head on the markers; softmax for a single-label task
count_logits	[1, 20]	instance count from [P]; extraction returns nothing when the argmax is 0
span_logits	[1, labels, words, 8]	instance-0 span scores (pre-sigmoid) for spans of 1–8 words

Entity decoding is the library's default: sigmoid ≥ 0.5, map word spans to characters, then keep spans greedily by confidence without character overlap. Entity extraction only reads instance 0, so the count GRU is unrolled once (export_onnx.py asserts that instance 0 does not depend on the unroll length).

Verification

conversion/reference.json holds 14 calls recorded from the Python gliner2 library (six goals across English and French, eight control-scoring calls on flight-search and maps pages), with their exact token ids. Against it:

dtype	same entities / top label	worst Δ (classify p / entity confidence)
fp32	14/14	1e-5 / 5e-7
fp16	14/14	3.3e-3 / 1.3e-4

The JavaScript runtime reproduces the token ids exactly. On WebGPU (fp16, Apple M3 Pro): 35–37 ms per extraction with nine entity types, 43–44 ms per classification with twelve labels.

Rebuilding

pip install torch "gliner2[local]" onnx onnxruntime onnxscript transformers
python conversion/reference.py        # Python reference outputs
python conversion/export_onnx.py      # fp32 graph
python conversion/convert_fp16.py     # fp16 graph
python conversion/verify_onnx.py      # parity check

(The scripts write to dist-model/; external data is renamed to the .onnx_data convention afterwards.)

Credits

Model by Fastino (GLiNER2), Apache-2.0. The agent calls these outputs serve come from gliner2-ultrafast (MIT).