maghwa (Marwa El Kamil)

upvoted an article 28 days ago

Article

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Apr 19

• 114

upvoted a collection 2 months ago

Arabic Aya DPO Datasets

Collection

Our synthetic DPO datasets for Arabic Aya. • 5 items • Updated Jun 4 • 4

upvoted a paper 4 months ago

101 Billion Arabic Words Dataset

Paper • 2405.01590 • Published Apr 29 • 5

upvoted an article 4 months ago

Article

Tokenization Is A Dead Weight (Tokun Part 1)

By

•

Jun 27

• 16

upvoted 2 papers 5 months ago

Tokenization Falling Short: The Curse of Tokenization

Paper • 2406.11687 • Published Jun 17 • 15

CroissantLLM: A Truly Bilingual French-English Language Model

Paper • 2402.00786 • Published Feb 1 • 25

upvoted an article 5 months ago

Article

🥐CroissantLLM: A Truly Bilingual French-English Language Model

By

•

Feb 5

• 10

upvoted a collection 5 months ago

FrenchBench Evaluation datasets

Collection

These datasets are used to evaluate models on French performance using: https://github.com/EleutherAI/lm-evaluation-harness (from CroissantLLM paper) • 11 items • Updated Jun 7 • 4

upvoted an article 5 months ago

Article

Introducing the Open Arabic LLM Leaderboard

May 14

• 67

upvoted a paper 5 months ago

Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

Paper • 2306.05685 • Published Jun 9, 2023 • 29

upvoted an article 5 months ago

Article

Let's talk about LLM evaluation

By

•

May 23

• 134

upvoted an article 6 months ago

Article

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

Apr 4

• 23

upvoted a paper 7 months ago

Dynamic Typography: Bringing Words to Life

Paper • 2404.11614 • Published Apr 17 • 43

upvoted 2 papers 9 months ago

BloombergGPT: A Large Language Model for Finance

Paper • 2303.17564 • Published Mar 30, 2023 • 20

Mistral 7B

Paper • 2310.06825 • Published Oct 10, 2023 • 47

Marwa El Kamil

AI & ML interests

Organizations

maghwa's activity

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Arabic Aya DPO Datasets

101 Billion Arabic Words Dataset

Tokenization Is A Dead Weight (Tokun Part 1)

Tokenization Falling Short: The Curse of Tokenization

CroissantLLM: A Truly Bilingual French-English Language Model

🥐CroissantLLM: A Truly Bilingual French-English Language Model

FrenchBench Evaluation datasets

Introducing the Open Arabic LLM Leaderboard

Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

Let's talk about LLM evaluation

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

Dynamic Typography: Bringing Words to Life

BloombergGPT: A Large Language Model for Finance

Mistral 7B