Article
21
Hippolyte Gisserot-Boukhlef
hgissbkh
AI & ML interests
NLP, Information Retrieval, Uncertainty Estimation
Recent Activity
commented on
a paper
about 2 months ago
Should We Still Pretrain Encoders with Masked Language Modeling?
updated
a Space
about 2 months ago
MLMvsCLM/README
upvoted
a
paper
2 months ago
Should We Still Pretrain Encoders with Masked Language Modeling?
Organizations
Articles 2
Article
146
Introducing EuroBERT: A High-Performance Multilingual Encoder Model
-
Should We Still Pretrain Encoders with Masked Language Modeling?
Paper • 2507.00994 • Published • 78 -
MLMvsCLM/610m-mlm40-42k-10000
Feature Extraction • Updated • 2 -
MLMvsCLM/610m-clm-40k-mlm20-42k
Feature Extraction • Updated • 4 -
MLMvsCLM/1b-mlm40-42k
Feature Extraction • Updated • 2
-
EuroBERT: Scaling Multilingual Encoders for European Languages
Paper • 2503.05500 • Published • 81 -
EuroBERT/EuroBERT-210m
Fill-Mask • 0.3B • Updated • 13.8k • 76 -
EuroBERT/EuroBERT-610m
Fill-Mask • 0.8B • Updated • 32.1k • 31 -
EuroBERT/EuroBERT-2.1B
Fill-Mask • 2B • Updated • 413 • 60
-
Should We Still Pretrain Encoders with Masked Language Modeling?
Paper • 2507.00994 • Published • 78 -
MLMvsCLM/610m-mlm40-42k-10000
Feature Extraction • Updated • 2 -
MLMvsCLM/610m-clm-40k-mlm20-42k
Feature Extraction • Updated • 4 -
MLMvsCLM/1b-mlm40-42k
Feature Extraction • Updated • 2
-
EuroBERT: Scaling Multilingual Encoders for European Languages
Paper • 2503.05500 • Published • 81 -
EuroBERT/EuroBERT-210m
Fill-Mask • 0.3B • Updated • 13.8k • 76 -
EuroBERT/EuroBERT-610m
Fill-Mask • 0.8B • Updated • 32.1k • 31 -
EuroBERT/EuroBERT-2.1B
Fill-Mask • 2B • Updated • 413 • 60
models
32
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-No-GPT-4
Text Generation
•
13B
•
Updated
•
5
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-No-Base
Text Generation
•
13B
•
Updated
•
3
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-No-Ref
Text Generation
•
13B
•
Updated
•
9
hgissbkh/ALMA-13B-LoRA-CPO-xCOMET-QE-Multi-No-GPT-4
Text Generation
•
13B
•
Updated
•
6
hgissbkh/ALMA-13B-LoRA-CPO-xCOMET-QE-Multi-No-Base
Text Generation
•
13B
•
Updated
•
7
hgissbkh/ALMA-13B-LoRA-CPO-xCOMET-QE-Multi-No-Ref
Text Generation
•
13B
•
Updated
•
4
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Mono
Text Generation
•
13B
•
Updated
•
5
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Multi-Choose-GPT-4
Text Generation
•
13B
•
Updated
•
4
hgissbkh/ALMA-13B-LoRA-SFT-chrF-Multi
Text Generation
•
13B
•
Updated
•
7
hgissbkh/ALMA-13B-LoRA-CPO-chrF-Multi
Text Generation
•
13B
•
Updated
•
5
datasets
42
hgissbkh/qed
Viewer
•
Updated
•
8.99k
•
4
hgissbkh/record
Viewer
•
Updated
•
111k
•
387
hgissbkh/uner_en
Viewer
•
Updated
•
16.6k
•
205
hgissbkh/mldr-en
Viewer
•
Updated
•
211k
•
269
hgissbkh/ontonotes5
Viewer
•
Updated
•
76.7k
•
250
hgissbkh/pos
Viewer
•
Updated
•
57.6k
•
6
hgissbkh/conll2003-en
Viewer
•
Updated
•
20.7k
•
239
hgissbkh/flores-200-10-lps
Viewer
•
Updated
•
20.2k
•
14
hgissbkh/msmarco-pairs
Viewer
•
Updated
•
503k
•
186
hgissbkh/ms_marco_10k
Viewer
•
Updated
•
248k
•
19