Ali El Filali

alielfilali01

AI & ML interests

AI Psychometrician ? | NLP (mainly for Arabic) | Other interests include Reinforcement Learning and Cognitive sciences among others

Recent Activity

updated a dataset 1 day ago

OALL/requests

liked a dataset 2 days ago

atlasia/TerjamaBench

updated a dataset 2 days ago

inceptionai/requests-dataset

View all activity

Articles

Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard

Dec 4, 2024

• 30

Introducing the Open Arabic LLM Leaderboard

May 14, 2024

• 77

Organizations

alielfilali01's activity

updated a dataset 1 day ago

OALL/requests

Updated about 22 hours ago • 6.62k

liked a dataset 2 days ago

atlasia/TerjamaBench

Viewer • Updated 2 days ago • 1.7k • 98 • 10

updated a dataset 2 days ago

inceptionai/requests-dataset

Viewer • Updated 2 days ago • 56 • 1.76k • 1

liked a Space 3 days ago

Running

🥇

Ad-dabit Arabic Diacritizer

Accurate Arabic Text Diacritizer (Tashkeel)

Running

331

📈

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though

Paper • 2501.04682 • Published 4 days ago • 72

liked 2 Spaces 5 days ago

Running

🐠

K2 Eval Gallery

reacted to MohamedRashad's post with ❤️ 6 days ago

Post

1754

The winners of Best Paper Award in NeurIPs2024 (FoundationVision) Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (2404.02905) has just released a new paper called infinty:
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (2412.04431)

And i managed to build a space for it so anyone can try it out: MohamedRashad/Infinity

The idea of a text to image model using autoregressive archticture is quite interesting in my opinion.

posted an update 6 days ago

Post

1720

3C3H AraGen Leaderboard welcomes today deepseek-ai/DeepSeek-V3 and 12 other models (including the late gpt-3.5 💀) to the ranking of best LLMs in Arabic !

Observations:
- DeepSeek-v3 ranked 3rd and only Open model among the top 5 !

- A 14B open model ( Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem !

- Contrary to what observed in likelihood-acc leaderboards (like OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model Qwen/Qwen2.5-32B-Instruct.
It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining.
Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...)

Check out the latest rankings: inceptionai/AraGen-Leaderboard

updated a Space 6 days ago

Running

📊

AraGen Leaderboard

Generative Tasks Evaluation of Arabic LLMs

reacted to prithivMLmods's post with 🚀 6 days ago

Post

5445

Reasoning SmolLM2 🚀

🎯Fine-tuning SmolLM2 on a lightweight synthetic reasoning dataset for reasoning-specific tasks. Future updates will focus on lightweight, blazing-fast reasoning models. Until then, check out the blog for fine-tuning details.

🔥Blog : https://huggingface.co/blog/prithivMLmods/smollm2-ft

🔼 Models :
+ SmolLM2-CoT-360M : prithivMLmods/SmolLM2-CoT-360M
+ Reasoning-SmolLM2-135M : prithivMLmods/Reasoning-SmolLM2-135M
+ SmolLM2-CoT-360M-GGUF : prithivMLmods/SmolLM2-CoT-360M-GGUF

🤠 Other Details :
+ Demo : prithivMLmods/SmolLM2-CoT-360M
+ Fine-tune nB : prithivMLmods/SmolLM2-CoT-360M