Downloads · 30 days
231
0% of all-time downloads
xlm-roberta-comet-small
Unbabel/xlm-roberta-comet-small
xlm-roberta-comet-small is a feature extraction model from Unbabel. Use it when you need embeddings to search or compare text. It is set up for transformers.
mMiniLM-L12xH384 XLM-R model proposed in MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers that we fine-tune using the direct assessment annotations collected in the Wor…
All-time downloads
128K
Public
Repo size
860 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin427 MB · 97%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- xlm-roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jul 10, 2021
- SHA
- df568a01
Model card
From the Hugging Face model README
Model
mMiniLM-L12xH384 XLM-R model proposed in MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers that we fine-tune using the direct assessment annotations collected in the Workshop on Statistical Machine Translation (WMT) 2015 to 2020.
This model is much more light weight than the traditional XLM-RoBERTa base and large.
- Task
- Feature Extraction
- Library
- transformers
- Type
- xlm-roberta
- Created
- Mar 2, 2022
- Updated
- Jul 10, 2021