Emmanuel Malherbe

emmanuelmalherbe's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 collections about 2 months ago

MLM versus CLM for NLP tasks

Collection

Related paper: "Should We Still Pretrain Encoders with Masked Language Modeling?" • 1 item • Updated Sep 11

EuroBERT Encoding model

Collection

Suite of models for improved integration into RAG (for information retrieval), designed for ease-of-use and practicability in industrial context • 5 items • Updated Sep 11 • 1

upvoted a collection about 2 months ago

EuroBERT Encoding model

Collection

Suite of models for improved integration into RAG (for information retrieval), designed for ease-of-use and practicability in industrial context • 5 items • Updated Sep 11 • 1

updated a Space about 2 months ago

Running

README

👀

liked 3 models 2 months ago

EuroBERT/EuroBERT-2.1B

Fill-Mask • 2B • Updated 15 days ago • 369 • 63

EuroBERT/EuroBERT-610m

Fill-Mask • 0.8B • Updated 15 days ago • 1.9k • 32

EuroBERT/EuroBERT-210m

Fill-Mask • 0.3B • Updated 15 days ago • 17.6k • 77

liked a dataset 2 months ago

artefactory/Argimi-Legal-French-Jurisprudence

Viewer • Updated Jul 22 • 768k • 301 • 6

upvoted a paper 4 months ago

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1 • 78

authored a paper 4 months ago

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1 • 78

updated 3 collections 7 months ago

Abstention Reranking

Collection

Related paper: "Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism" (accepted at TMLR 2024) • 3 items • Updated Apr 10

EuroBERT

Collection

Suite of Encoder models EuroBERT • 4 items • Updated Apr 10 • 1

EuroBERT Encoding model

Collection

Suite of models for improved integration into RAG (for information retrieval), designed for ease-of-use and practicability in industrial context • 5 items • Updated Sep 11 • 1

upvoted a paper 7 months ago

MMTEB: Massive Multilingual Text Embedding Benchmark

Paper • 2502.13595 • Published Feb 19 • 41

updated 2 collections 7 months ago

EuroBERT Encoding model

Collection

Suite of models for improved integration into RAG (for information retrieval), designed for ease-of-use and practicability in industrial context • 5 items • Updated Sep 11 • 1

EuroBERT

Collection

Suite of Encoder models EuroBERT • 4 items • Updated Apr 10 • 1

updated a collection 8 months ago

EuroBERT

Collection

Suite of Encoder models EuroBERT • 4 items • Updated Apr 10 • 1