-
jaygala24/Qwen3-4B-GRPO-KL-math-reasoning
Text Generation • 4B • Updated • 619 -
jaygala24/Qwen3-4B-GRPO-math-reasoning
Text Generation • 4B • Updated • 505 -
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 501 -
jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 522
Jay Gala
jaygala24
AI & ML interests
Machine Learning, Natural Language Processing, Language and Vision Intersection, Fairness and Biases
Recent Activity
updated a collection 1 day ago
RL post-training updated a collection 1 day ago
RL post-training updated a collection 1 day ago
RL post-trainingOrganizations
-
jaygala24/Qwen3-4B-GRPO-KL-math-reasoning
Text Generation • 4B • Updated • 619 -
jaygala24/Qwen3-4B-GRPO-math-reasoning
Text Generation • 4B • Updated • 505 -
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 501 -
jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 522
models 17
jaygala24/Qwen2.5-3B-ReMax-math-reasoning
Text Generation • 3B • Updated • 194
jaygala24/Qwen2.5-1.5B-ReMax-math-reasoning
Text Generation • 2B • Updated • 180
jaygala24/Qwen2.5-0.5B-ReMax-math-reasoning
Text Generation • 0.5B • Updated • 189
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 501
jaygala24/Qwen3-1.7B-ReMax-math-reasoning
Text Generation • 2B • Updated • 561
jaygala24/Qwen2.5-1.5B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 247
jaygala24/Qwen2.5-1.5B-GRPO-math-reasoning
Text Generation • 2B • Updated • 296
jaygala24/Qwen2.5-0.5B-GRPO-KL-math-reasoning
Text Generation • 0.5B • Updated • 275
jaygala24/Qwen2.5-0.5B-GRPO-math-reasoning
Text Generation • 0.5B • Updated • 297
jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 522