elkahtib's picture

elkahtib

Abdelkareem

·

https://kareemai.com

AI & ML interests

“فتًى جاهدَ الدّنيا وجاهد أهلَها وفي نفسهِ لم يَدرِ كيف يجاهدُ” https://gpuvec.com

Recent Activity

liked a model 4 days ago

jinaai/jina-code-embeddings-0.5b

upvoted a collection 4 days ago

jina-code-embeddings

liked a dataset 5 days ago

jupyter-agent/jupyter-agent-dataset

View all activity

Organizations

upvoted a collection 4 days ago

jina-code-embeddings

high quality code embeddings trained from code generation models • 5 items • Updated 6 days ago • 11

upvoted 2 collections 3 months ago

Zaraah | Static Arabic Embedding Models

This blog post introduces the Zaraah family of static embedding models, designed for Arabic language tasks and built using the model2vec distillation • 10 items • Updated Jun 16 • 2

Audio Codecs Embeddings 🎙️

A collection of codec and embedding models supported in 🤗 Transformers. • 5 items • Updated Jul 17, 2024 • 4

upvoted 2 collections 4 months ago

Falcon-Arabic

7B models built on top of Falcon3-7B • 3 items • Updated Jul 23 • 10

Chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR. • 2 items • Updated Jul 9, 2024 • 32

upvoted 2 collections 5 months ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 209

Describe Anything

Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 7 items • Updated 7 days ago • 56

upvoted 2 articles 5 months ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

Oct 27, 2024

• 41

Article

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

By

and 1 other •

Oct 14, 2024

• 97

upvoted 3 collections 5 months ago

Multimodal DSE Retrievers

A collection of DSE models for multimodal retrieval • 5 items • Updated Apr 15 • 15

PubMedBERT Embeddings M2V

Models distilled with Model2Vec - 100K / 500K / 1M / 2M / 8M parameter variants. • 5 items • Updated Jan 26 • 4

Orpheus Multilingual Research Release

Beta Release of multilingual models. • 12 items • Updated Apr 10 • 100

upvoted 2 articles 6 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

By

•

Mar 26

• 161

Article

ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

By

and 2 others •

Mar 18

• 11

upvoted 2 collections 6 months ago

📚 LLM pretraining datasets

A collection of datasets for LLM pretraining • 9 items • Updated May 5 • 11

SmolDocling

3 items • Updated Apr 7 • 9

upvoted an article 6 months ago

Article

Xet is on the Hub

By

and 5 others •

Mar 18

• 69

upvoted 3 collections 6 months ago

Gemma 3 Release

28 items • Updated 30 days ago • 494

Dar Datasets

datasets uploaded by https://github.com/ARBML/dar • 200 items • Updated Aug 22, 2024 • 14

CAMEL-Bench

Arabic MultiModal Benchmark • 46 items • Updated Feb 2 • 9