1 38 197

Wassim Trabelsi PRO

wath5

https://www.wassimt.com

wassim-trabelsi

AI & ML interests

AI Engineer NLP & Computer Vision

Recent Activity

liked a Space 18 days ago

AdithyaSK/rl-environments-guide

liked a Space 18 days ago

systms/ACTION-HF

liked a Space 18 days ago

smolagents/ml-intern

View all activity

Organizations

liked 3 Spaces 18 days ago

The ultimate guide to RL environments: building and scaling them in the LLM era

📝

173

Building and scaling RL environments for LLM training

SYSTMS Action

⚡

Turn anything into an action figure or a toy

ML Intern

🤖

388

Get AI‑powered help with machine‑learning questions

liked a dataset 2 months ago

open-index/hacker-news

Updated 1 minute ago • 33.2k • 319

upvoted 2 articles 2 months ago

Article

History of State Space Models (SSM) in 2022

lbourdois

•

Apr 11, 2024

• 28

Article

Introduction to State Space Models (SSM)

lbourdois

•

Jul 19, 2024

• 226

upvoted a paper 2 months ago

dLLM: Simple Diffusion Language Modeling

Paper • 2602.22661 • Published Feb 26 • 153

upvoted an article 3 months ago

Article

Mixture of Experts (MoEs) in Transformers

ariG23498, pcuenq, merve, IlyasMoutawwakil, ArthurZ, sergiopaniego, Molbap

•

Feb 26

• 164

liked a model 3 months ago

mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • 4B • Updated Mar 11 • 1.26M • 860

upvoted 2 articles 4 months ago

Article

From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output

MaziyarPanahi

•

Feb 7

• 22

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

burtenshaw, SaylorTwift, kramp, merve, davanstrien, nielsr, julien-c

•

Feb 4

• 90

liked 2 models 4 months ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • 1.1T • Updated 28 days ago • 1.45M • • 2.8k

thebajajra/RexReranker-0.6B

Text Ranking • 0.6B • Updated Jan 24 • 3.66k • 10

upvoted an article 4 months ago

Article

RexRerankers: SOTA Rankers for Product Discovery and AI Assistants

thebajajra

•

Jan 24

• 44

reacted to danielhanchen's post with ❤️ 4 months ago

Post

2657

You can now fine-tune embedding models in our free Unsloth notebook! 🤗

Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data.

⭐ Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning

Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups.

We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!