Nicolas-BZRD

49 69 92

ntnq's profile picture

Zorryy's profile picture

BramVanroy's profile picture

https://nicolas-bzrd.github.io

N1colAIs
Nicolas-BZRD
nicolas-boizard

AI & ML interests

PhD Student | NLP - LLMs - Adaptation real-world problem Optimization

Recent Activity

upvoted a collection 2 days ago

MultiVectorEncoder integrations

upvoted an article 5 days ago

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

upvoted an article 10 days ago

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

View all activity

Organizations

Nicolas-BZRD 's collections 8

BidirLM

BidirLM is a family of 5 frontier bidirectional encoders, including an omnimodal variant at 2.5B.

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

Paper • 2604.02045 • Published Apr 2 • 39
BidirLM/BidirLM-Omni-2.5B-Embedding

Sentence Similarity • 2B • Updated May 12 • 926 • 46
BidirLM/BidirLM-1.7B-Embedding

Sentence Similarity • 2B • Updated Jun 8 • 2.92k • 7
BidirLM/BidirLM-1B-Embedding

Sentence Similarity • 1.0B • Updated Jun 8 • 468 • 4

EuroLLM 🇪🇺

EuroLLM-22B: Technical Report

Paper • 2602.05879 • Published Feb 5 • 3
EuroLLM-9B: Technical Report

Paper • 2506.04079 • Published Jun 4, 2025 • 1
utter-project/EuroLLM-22B-Instruct-2512

Text Generation • 23B • Updated 22 days ago • 5.57k • • 77
utter-project/EuroLLM-9B-Instruct

Text Generation • 9B • Updated Dec 9, 2024 • 42.6k • 215

BERT-as-a-Judge

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Paper • 2604.09497 • Published Apr 10 • 29
artefactory/BERTJudge

Text Classification • 0.2B • Updated Apr 16 • 40 • 8
artefactory/BERTJudge-Dataset

Updated Apr 16 • 2.26k • 2
BERT-as-a-Judge

Collection

10 items • Updated Apr 16 • 4

MLM vs CLM

Should We Still Pretrain Encoders with Masked Language Modeling?

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1, 2025 • 81
MLM vs CLM

Collection

65 items • Updated Sep 25, 2025 • 1

EuroBERT 🇪🇺

Scaling Multilingual Encoders for European Languages.

EuroBERT: Scaling Multilingual Encoders for European Languages

Paper • 2503.05500 • Published Mar 7, 2025 • 81
EuroBERT/EuroBERT-210m

Fill-Mask • 0.3B • Updated Oct 18, 2025 • 19.4k • 87
EuroBERT/EuroBERT-610m

Fill-Mask • 0.8B • Updated Oct 18, 2025 • 5.81k • 33
EuroBERT/EuroBERT-2.1B

Fill-Mask • 2B • Updated Oct 18, 2025 • 2.02k • 67

CroissantLLM 🥐

CroissantLLM: A Truly Bilingual French-English Language Model

CroissantLLM: A Truly Bilingual French-English Language Model

Paper • 2402.00786 • Published Feb 1, 2024 • 26
croissantllm/CroissantLLMChat-v0.1

Text Generation • 1B • Updated Apr 26, 2024 • 772 • 52
croissantllm/CroissantLLMBase

Text Generation • Updated Aug 30, 2024 • 922 • 36
croissantllm/croissant_dataset

Viewer • Updated Oct 3, 2024 • 16.7B • 17.9k • 8

When Does Reasoning Matter?

A Controlled Study of Reasoning's Contribution to Model Performance.

When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance

Paper • 2509.22193 • Published Sep 26, 2025 • 38
Scale-or-Reason/general-reasoning-ift-pairs

Viewer • Updated Jun 27 • 2.97M • 1.04k • 6
Scale-or-Reason/math-reasoning-ift-pairs

Viewer • Updated Jun 27 • 458k • 4.27k • 8

ULD Loss (Universal LLMs Distillation)

The ULD loss, based on optimal transport, enables distillation across different LLM families without requiring shared tokenizers.

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

Paper • 2402.12030 • Published Feb 19, 2024 • 4
mistralai/Mistral-7B-Instruct-v0.2

Text Generation • 7B • Updated Jul 24, 2025 • 1.17M • • 3.2k
meta-llama/Llama-2-7b-chat-hf

Text Generation • 7B • Updated Apr 17, 2024 • 539k • 4.82k
EleutherAI/pythia-160m-deduped

Text Generation • 0.2B • Updated Jul 9, 2023 • 433k • 4

BidirLM

BidirLM is a family of 5 frontier bidirectional encoders, including an omnimodal variant at 2.5B.

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

Paper • 2604.02045 • Published Apr 2 • 39
BidirLM/BidirLM-Omni-2.5B-Embedding

Sentence Similarity • 2B • Updated May 12 • 926 • 46
BidirLM/BidirLM-1.7B-Embedding

Sentence Similarity • 2B • Updated Jun 8 • 2.92k • 7
BidirLM/BidirLM-1B-Embedding

Sentence Similarity • 1.0B • Updated Jun 8 • 468 • 4

EuroBERT 🇪🇺

Scaling Multilingual Encoders for European Languages.

EuroBERT: Scaling Multilingual Encoders for European Languages

Paper • 2503.05500 • Published Mar 7, 2025 • 81
EuroBERT/EuroBERT-210m

Fill-Mask • 0.3B • Updated Oct 18, 2025 • 19.4k • 87
EuroBERT/EuroBERT-610m

Fill-Mask • 0.8B • Updated Oct 18, 2025 • 5.81k • 33
EuroBERT/EuroBERT-2.1B

Fill-Mask • 2B • Updated Oct 18, 2025 • 2.02k • 67

EuroLLM 🇪🇺

EuroLLM-22B: Technical Report

Paper • 2602.05879 • Published Feb 5 • 3
EuroLLM-9B: Technical Report

Paper • 2506.04079 • Published Jun 4, 2025 • 1
utter-project/EuroLLM-22B-Instruct-2512

Text Generation • 23B • Updated 22 days ago • 5.57k • • 77
utter-project/EuroLLM-9B-Instruct

Text Generation • 9B • Updated Dec 9, 2024 • 42.6k • 215

CroissantLLM 🥐

CroissantLLM: A Truly Bilingual French-English Language Model

CroissantLLM: A Truly Bilingual French-English Language Model

Paper • 2402.00786 • Published Feb 1, 2024 • 26
croissantllm/CroissantLLMChat-v0.1

Text Generation • 1B • Updated Apr 26, 2024 • 772 • 52
croissantllm/CroissantLLMBase

Text Generation • Updated Aug 30, 2024 • 922 • 36
croissantllm/croissant_dataset

Viewer • Updated Oct 3, 2024 • 16.7B • 17.9k • 8

BERT-as-a-Judge

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Paper • 2604.09497 • Published Apr 10 • 29
artefactory/BERTJudge

Text Classification • 0.2B • Updated Apr 16 • 40 • 8
artefactory/BERTJudge-Dataset

Updated Apr 16 • 2.26k • 2
BERT-as-a-Judge

Collection

10 items • Updated Apr 16 • 4

When Does Reasoning Matter?

A Controlled Study of Reasoning's Contribution to Model Performance.

When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance

Paper • 2509.22193 • Published Sep 26, 2025 • 38
Scale-or-Reason/general-reasoning-ift-pairs

Viewer • Updated Jun 27 • 2.97M • 1.04k • 6
Scale-or-Reason/math-reasoning-ift-pairs

Viewer • Updated Jun 27 • 458k • 4.27k • 8

MLM vs CLM

Should We Still Pretrain Encoders with Masked Language Modeling?

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1, 2025 • 81
MLM vs CLM

Collection

65 items • Updated Sep 25, 2025 • 1

ULD Loss (Universal LLMs Distillation)

The ULD loss, based on optimal transport, enables distillation across different LLM families without requiring shared tokenizers.

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

Paper • 2402.12030 • Published Feb 19, 2024 • 4
mistralai/Mistral-7B-Instruct-v0.2

Text Generation • 7B • Updated Jul 24, 2025 • 1.17M • • 3.2k
meta-llama/Llama-2-7b-chat-hf

Text Generation • 7B • Updated Apr 17, 2024 • 539k • 4.82k
EleutherAI/pythia-160m-deduped

Text Generation • 0.2B • Updated Jul 9, 2023 • 433k • 4