This is your work, valued
SynthCLIP. Code base of SynthCLIP: CLIP training with purely synthetic text-image pairs from LLMs and TTIs.
104DiffCLIP. Official Implementation of DiffCLIP: Differential Attention Meets CLIP
57CLDatasets. Python
22DiversitySSL. Original code base for On Pretraining Data Diversity for Self-Supervised Learning
14AraLingBench. Official Implementation of AraLingBench
9curriculum_grpo. A torchtune based implementation of curriculum grpo introduced in Train Long, Think Short: Curriculum Learning for Efficient Reasoning.
7SubthoughtReasoner.
6Hala. Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
5MergeAlign. Official implementation of Model Merging and Safety Alignment: One Bad Model Spoils the Bunch (EMNLP 2024)
3RACLora. Official Implementation of Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation
2