Faton Rekathati

Lauler

·

Lauler

AI & ML interests

None yet

Recent Activity

liked a dataset 3 days ago

KlangAI/klang-dialects

upvoted an article 26 days ago

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

liked a dataset 27 days ago

dell-research-harvard/AmericanStories

View all activity

Organizations

upvoted an article 26 days ago

Article

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

tomaarsen

•

27 days ago

• 144

upvoted an article about 1 month ago

Article

FineBooks: are open OCR models good enough to unlock historical knowledge?

finebooks

•

Aug 10

• 25

upvoted an article about 2 months ago

Article

mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models

lightonai

•

Jul 30

• 38

upvoted an article 4 months ago

Article

BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders

Nicolas-BZRD

•

Apr 7

• 28

upvoted 3 collections 5 months ago

Prism Reranker

5 items • Updated Apr 26 • 11

DenseOn & LateOn

A collection of open state-of-the-art single and multi-vector models for English retrieval • 9 items • Updated about 9 hours ago • 13

TIPSv2

TIPSv2 foundational vision-language models. Webpage: https://gdm-tipsv2.github.io/ • 9 items • Updated Jul 21 • 44

upvoted a paper 5 months ago

Embarrassingly Simple Self-Distillation Improves Code Generation

Paper • 2604.01193 • Published Apr 1 • 56

upvoted 2 articles 5 months ago

Article

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

tomaarsen

•

Apr 16

• 82

Article

easyaligner: Forced alignment of text and audio, made easy

KBLab

•

Apr 16

• 5

upvoted a collection 7 months ago

UltraData

Ultra Scale, Ultra Quality, Ultra Coverage • 19 items • Updated 7 days ago • 110

upvoted an article 7 months ago

Article

easytranscriber: Speech Recognition with Accurate Timestamps in the HF Ecosystem

KBLab

•

Mar 3

• 6

upvoted an article 8 months ago

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

zilliz

•

Jan 15

• 67

upvoted a collection 9 months ago

Nemotron-Post-Training-v3

Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated Aug 11 • 202

upvoted 2 collections about 1 year ago

Common Pile v0.1 Filtered Data

An LLM pre-training dataset produced by filtering and deduplicating the raw text collected in the Common Pile v0.1 • 31 items • Updated Jun 6, 2025 • 27

Reward Models 06-2025

Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge • 8 items • Updated Aug 11 • 25

upvoted a paper over 1 year ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7, 2025 • 212

upvoted an article over 1 year ago

Article

Training and Finetuning Reranker Models with Sentence Transformers

tomaarsen

•

Mar 26, 2025

• 197

upvoted a collection over 1 year ago

reranking series v2

V2 crispy rerank series • 3 items • Updated May 21 • 25

upvoted a paper over 2 years ago

Analyzing and Improving the Training Dynamics of Diffusion Models

Paper • 2312.02696 • Published Dec 5, 2023 • 33