Downloads · 30 days
0
xlm-roberta-base-onnx-int8
lelloman/xlm-roberta-base-onnx-int8
xlm-roberta-base-onnx-int8 is a machine learning model from lelloman. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
INT8 quantized ONNX export of xlm-roberta-base for efficient on-device inference.
Access
Public
Updated Dec 31, 2025
Repo size
534 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx534 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Dec 31, 2025
- Updated
- Dec 31, 2025
- SHA
- 322d939b
Model card
From the Hugging Face model README
XLM-RoBERTa Base ONNX (INT8 Quantized)
INT8 quantized ONNX export of xlm-roberta-base for efficient on-device inference.
Model Details
- Base model: xlm-roberta-base (278M params)
- Format: ONNX
- Quantization: INT8 dynamic quantization
- Size: ~509MB (vs ~1.1GB unquantized)
Usage
This model is designed for use with LoRA adapters applied at runtime. The weights are exported with do_constant_folding=False to allow in-memory patching.
Files
xlm_roberta_base_int8.onnx- INT8 quantized ONNX model
Export Details
Exported using:
- transformers
- optimum
- onnxruntime
With dynamic INT8 quantization for reduced model size while maintaining accuracy.
- License
- mit
- Created
- Dec 31, 2025
- Updated
- Dec 31, 2025