Downloads · 30 days
31
4% of all-time downloads
xlm-roberta-base-ance-en-jp-warmup
k-ush/xlm-roberta-base-ance-en-jp-warmup
xlm-roberta-base-ance-en-jp-warmup is a sentence similarity model from k-ush. Use it when you need a score for how close two texts are. It is set up for transformers. The card lists the license as openrail.
A XLM-RoBERTa-base model trained on mMARCO Japanese dataset with ANCE warmup script. Base checkpoint comes from k-ush/xlm-roberta-base-ance-warmup, so this model was trained both English and Japanese data.
All-time downloads
800
Public
Repo size
4.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt2.2 GB · 67%
At a glance
- Task
- Sentence Similarity
- Library
- transformers
- License
- openrail
- Model type
- xlm-roberta
- Access
- Public
- Created
- Feb 19, 2023
- Updated
- Feb 22, 2023
- SHA
- 33c0736f
Datasets
Model card
From the Hugging Face model README
k-ush/xlm-roberta-base-ance-en-jp-warmup
A XLM-RoBERTa-base model trained on mMARCO Japanese dataset with ANCE warmup script. Base checkpoint comes from k-ush/xlm-roberta-base-ance-warmup, so this model was trained both English and Japanese data. I upload checkpoint at 50k steps since MRR@100 at 60k checkpoint was decrease (mrr@100(rerank, full): 0.242, 0.182).
Dataset
I formmated Japanese mMarco dataset for ANCE. Dataset preparetion script is available on github. https://github.com/argonism/JANCE/blob/master/data/gen_jp_data.py
Evaluation Result
Evaluation Result during trainning with mMarco Japanese dev set.
Reranking/Full ranking mrr: 0.24208174148360342/0.19015224905626082
- Task
- Sentence Similarity
- Library
- transformers
- Type
- xlm-roberta
- License
- openrail
- Languages
- ja, en
- Created
- Feb 19, 2023
- Updated
- Feb 22, 2023