dbmdz/bert-base-german-uncased
Fill-Mask
•
0.1B
•
Updated
•
4.44k
•
•
28
Marc Olejak
MarcGrumpyOlejak
AI & ML interests
On the practical low-cost level of ML playing around with german bureaucratic language and still uses Levenshtein.
Recent Activity
liked
a model
4 days ago
dbmdz/bert-base-german-uncased
liked
a dataset
20 days ago
PleIAs/SYNTH
updated
a dataset
21 days ago
MarcGrumpyOlejak/gooaq_mt_german
Organizations
None yet
liked
a
model
4 days ago
liked
a
dataset
20 days ago
updated
a
dataset
21 days ago
Have you tried your dataset for other models?
#1 opened 23 days ago
by
MarcGrumpyOlejak
upvoted
an
article
about 1 month ago
Article
Sentence Transformers is joining Hugging Face!
•
85
upvoted
an
article
about 2 months ago
Article
Training and Finetuning Reranker Models with Sentence Transformers v4
•
176
liked
a
model
about 2 months ago
upvoted
an
article
2 months ago
Article
mmBERT: ModernBERT goes Multilingual
- +4
•
130
reacted to
tomaarsen's
post with ❤️
2 months ago
Post
5706
ModernBERT goes MULTILINGUAL! One of the most requested models I've seen, The Johns Hopkins University's CLSP has trained state-of-the-art massively multilingual encoders using the ModernBERT architecture: mmBERT.
Model details:
- 2 model sizes:
- jhu-clsp/mmBERT-small
- jhu-clsp/mmBERT-base
- Uses the ModernBERT architecture, but with the Gemma2 multilingual tokenizer (so: flash attention, alternating global/local attention, unpadding/sequence packing, etc.)
- Maximum sequence length of 8192 tokens, on the high end for encoders
- Trained on 1833 languages using DCLM, FineWeb2, and many more sources
- 3 training phases: 2.3T tokens pretraining on 60 languages, 600B tokens mid-training on 110 languages, and 100B tokens decay training on all 1833 languages.
- Both models are MIT Licensed, and the full datasets and intermediary checkpoints are also publicly released
Evaluation details:
- Very competitive with ModernBERT at equivalent sizes on English (GLUE, MTEB v2 English after finetuning)
- Consistently outperforms equivalently sized models on all Multilingual tasks (XTREME, classification, MTEB v2 Multilingual after finetuning)
- In short: beats commonly used multilingual base models like mDistilBERT, XLM-R (multilingual RoBERTa), multilingual MiniLM, etc.
- Additionally: the ModernBERT-based mmBERT is much faster than the alternatives due to its architectural benefits. Easily up to 2x throughput in common scenarios.
Check out the full blogpost with more details. It's super dense & gets straight to the point: https://huggingface.co/blog/mmbert
Based on these results, mmBERT should be the new go-to multilingual encoder base models at 300M and below. Do note that the mmBERT models are "base" models, i.e. they're currently only trained to perform Mask Filling. They'll need to be finetuned for downstream tasks like semantic search, classification, clustering, etc.
Model details:
- 2 model sizes:
- jhu-clsp/mmBERT-small
- jhu-clsp/mmBERT-base
- Uses the ModernBERT architecture, but with the Gemma2 multilingual tokenizer (so: flash attention, alternating global/local attention, unpadding/sequence packing, etc.)
- Maximum sequence length of 8192 tokens, on the high end for encoders
- Trained on 1833 languages using DCLM, FineWeb2, and many more sources
- 3 training phases: 2.3T tokens pretraining on 60 languages, 600B tokens mid-training on 110 languages, and 100B tokens decay training on all 1833 languages.
- Both models are MIT Licensed, and the full datasets and intermediary checkpoints are also publicly released
Evaluation details:
- Very competitive with ModernBERT at equivalent sizes on English (GLUE, MTEB v2 English after finetuning)
- Consistently outperforms equivalently sized models on all Multilingual tasks (XTREME, classification, MTEB v2 Multilingual after finetuning)
- In short: beats commonly used multilingual base models like mDistilBERT, XLM-R (multilingual RoBERTa), multilingual MiniLM, etc.
- Additionally: the ModernBERT-based mmBERT is much faster than the alternatives due to its architectural benefits. Easily up to 2x throughput in common scenarios.
Check out the full blogpost with more details. It's super dense & gets straight to the point: https://huggingface.co/blog/mmbert
Based on these results, mmBERT should be the new go-to multilingual encoder base models at 300M and below. Do note that the mmBERT models are "base" models, i.e. they're currently only trained to perform Mask Filling. They'll need to be finetuned for downstream tasks like semantic search, classification, clustering, etc.
reacted to
tomaarsen's
post with ❤️
3 months ago
Post
4430
😎 I just published Sentence Transformers v5.1.0, and it's a big one. 2x-3x speedups of SparseEncoder models via ONNX and/or OpenVINO backends, easier distillation data preparation with hard negatives mining, and more:
1️⃣ Faster ONNX and OpenVINO backends for SparseEncoder models
Usage is as simple as
2️⃣ New
This new output format is immediately compatible with the MarginMSELoss and SparseMarginMSELoss for training SentenceTransformer, CrossEncoder, and SparseEncoder losses.
3️⃣ Gathering across devices
When doing multi-GPU training using a loss that has in-batch negatives (e.g. MultipleNegativesRankingLoss), you can now use
4️⃣ Trackio support
If you also upgrade
5️⃣ MTEB Documentation
We've added some documentation on evaluating SentenceTransformer models properly with MTEB. It's rudimentary as the documentation on the MTEB side is already great, but it should get you started.
Plus many more smaller features & fixes (crash fixes, compatibility with datasets v4, FIPS compatibility, etc.).
See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v5.1.0
Big thanks to all of the contributors for helping with the release, many of the features from this release were proposed by others. I have a big list of future potential features that I'd love to add, but I'm
1️⃣ Faster ONNX and OpenVINO backends for SparseEncoder models
Usage is as simple as
backend="onnx" or backend="openvino" when initializing a SparseEncoder to get started, but I also included utility functions for optimization, dynamic quantization, and static quantization, plus benchmarks.2️⃣ New
n-tuple-scores output format from mine_hard_negativesThis new output format is immediately compatible with the MarginMSELoss and SparseMarginMSELoss for training SentenceTransformer, CrossEncoder, and SparseEncoder losses.
3️⃣ Gathering across devices
When doing multi-GPU training using a loss that has in-batch negatives (e.g. MultipleNegativesRankingLoss), you can now use
gather_across_devices=True to load in-batch negatives from the other devices too! Essentially a free lunch, pretty big impact potential in my evals.4️⃣ Trackio support
If you also upgrade
transformers, and you install trackio with pip install trackio, then your experiments will also automatically be tracked locally with trackio. Just open up localhost and have a look at your losses/evals, no logins, no metric uploading.5️⃣ MTEB Documentation
We've added some documentation on evaluating SentenceTransformer models properly with MTEB. It's rudimentary as the documentation on the MTEB side is already great, but it should get you started.
Plus many more smaller features & fixes (crash fixes, compatibility with datasets v4, FIPS compatibility, etc.).
See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v5.1.0
Big thanks to all of the contributors for helping with the release, many of the features from this release were proposed by others. I have a big list of future potential features that I'd love to add, but I'm
liked
a
dataset
4 months ago
upvoted
a
collection
4 months ago
updated
a
dataset
4 months ago
This dataset has 2 files scanned as unsafe.
1
#2 opened 4 months ago
by
MarcGrumpyOlejak
[bot] Conversion to Parquet
#1 opened 4 months ago
by
parquet-converter
A small typo in your example to build a training set.
#3 opened 4 months ago
by
MarcGrumpyOlejak
published
a
dataset
4 months ago
updated
2
datasets
4 months ago