Basbas Mounir

wahidmounir

·

wahidmounir

AI & ML interests

Ai, LLM

Recent Activity

updated a collection about 12 hours ago

updated a collection 1 day ago

updated a collection 1 day ago

View all activity

Organizations

None yet

upvoted a collection 6 days ago

ModernBERT

Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated Dec 19, 2024 • 161

upvoted 2 papers about 1 month ago

olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

Paper • 2502.18443 • Published Feb 25, 2025 • 13

Geometric Context Transformer for Streaming 3D Reconstruction

Paper • 2604.14141 • Published Apr 15 • 38

upvoted a collection about 1 month ago

Physics of Language Models: Part 4.2

16 items • Updated Jul 29, 2025 • 20

upvoted an article 4 months ago

Article

Reproducing and Validating Distributed Muon 🐢✨: A Practical Verification of Communication Efficiency Claims

bird-of-paradise

•

Dec 12, 2025

• 2

upvoted 2 collections 5 months ago

Nemotron-Pre-Training-Datasets

Large scale pre-training datasets used in the Nemotron family of models. • 15 items • Updated 12 days ago • 183

Qwen3.5

21 items • Updated Mar 9 • 1.75k

upvoted a paper 6 months ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published Jan 30 • 229

upvoted 12 collections 6 months ago

Leaderboards for Arabic

A collection for all leaderboards related to the Arabic Language. • 5 items • Updated Dec 9, 2025 • 8

FineTuned

45 items • Updated Jul 3 • 1

Translation

78 items • Updated 14 days ago • 1

LTX2

18 items • Updated 10 days ago • 1

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 20 days ago • 219

ZeroGPU Spaces

ZeroGPU Spaces made by the community • 17 items • Updated Jun 6, 2024 • 249

Qwen3-TTS

7 items • Updated Jan 22 • 379

DeepSeek-V3.1

3 items • Updated Mar 2 • 264

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 70 items • Updated about 13 hours ago • 277

Gemma 3n

4 items • Updated 20 days ago • 274

EAGLE3

The collection of eagle3 series models for Qwen3 and Hunyuan. • 15 items • Updated Jan 13 • 5

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 115 items • Updated about 13 hours ago • 800