-
jaygala24/Qwen3-4B-GRPO-KL-math-reasoning
Text Generation • 4B • Updated • 11 -
jaygala24/Qwen3-4B-GRPO-math-reasoning
Text Generation • 4B • Updated • 15 -
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 13 -
jaygala24/Qwen3-4B-RLOO-math-reasoning
Text Generation • 4B • Updated • 8
Jay Gala
jaygala24
AI & ML interests
Machine Learning, Natural Language Processing, Language and Vision Intersection, Fairness and Biases
Recent Activity
updated a collection about 4 hours ago
EchoMoE upvoted a paper about 4 hours ago
Communicate the Change: Efficient Expert Parallelism via Activation Compression updated a model about 21 hours ago
McGill-NLP/EchoMoE