xa2go/xlm-roberta-large-lemma-eu-onnx-int8
By xa2go · ↓ 3 · ♥ 0 · Updated 2026-01-26
What's in this repo
This page lists the files in xa2go/xlm-roberta-large-lemma-eu-onnx-int8, including model.onnx.
- 1 ONNX models (.onnx files)
- 8 files, including 5 .json, 1 .md, 1 .onnx
- Last updated 2026-01-26
ONNX files
| File | Size | Download |
|---|---|---|
| model.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
XLM-RoBERTa Large Lemmatizer (ONNX INT8)
Optimized model for CPU inference.
Usage
from optimum.onnxruntime import ORTModelForTokenClassification
from transformers import AutoTokenizer
model = ORTModelForTokenClassification.from_pretrained("xa2go/xlm-roberta-large-lemma-eu-onnx-int8")
tokenizer = AutoTokenizer.from_pretrained("xa2go/xlm-roberta-large-lemma-eu-onnx-int8")
text = "Euskal Herriko Unibertsitatea Bilboko campusean dago."
inputs = tokenizer(text, return_tensors="np")
outputs = model(**inputs)
Características
- Format: ONNX INT8 quantized
- Optimizado: AVX2 (AMD EPYC, Intel Xeon)
- Speedup: 2-3x vs FP32
- Tamaño: 75% reducción
Model info
token-classification
optimum
optimum
onnx
xlm-roberta
token-classification
lemmatization
int8
quantized
eu
base_model:HiTZ/xlm-roberta-large-lemma-eu
base_model:quantized:HiTZ/xlm-roberta-large-lemma-eu
license:mit
region:us
↓ 3
♥ 0
Created: 2026-01-26
Updated: 2026-01-26
View on Hugging FaceFiles (8)
.gitattributes
README.md
config.json
model.onnx
ONNX
ort_config.json
special_tokens_map.json
tokenizer.json
tokenizer_config.json
Related models
More from xa2go
No other models by this author.