-
jaygala24/Qwen3-4B-GRPO-KL-math-reasoning
Text Generation • 4B • Updated • 621 -
jaygala24/Qwen3-4B-GRPO-math-reasoning
Text Generation • 4B • Updated • 508 -
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 503 -
jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 524
Jay Gala
jaygala24
AI & ML interests
Machine Learning, Natural Language Processing, Language and Vision Intersection, Fairness and Biases
Recent Activity
updated a collection 2 days ago
RL post-training updated a collection 2 days ago
RL post-training updated a collection 2 days ago
RL post-trainingOrganizations
-
jaygala24/Qwen3-4B-GRPO-KL-math-reasoning
Text Generation • 4B • Updated • 621 -
jaygala24/Qwen3-4B-GRPO-math-reasoning
Text Generation • 4B • Updated • 508 -
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 503 -
jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 524
models 17
jaygala24/Qwen2.5-3B-ReMax-math-reasoning
Text Generation • 3B • Updated • 195
jaygala24/Qwen2.5-1.5B-ReMax-math-reasoning
Text Generation • 2B • Updated • 181
jaygala24/Qwen2.5-0.5B-ReMax-math-reasoning
Text Generation • 0.5B • Updated • 189
jaygala24/Qwen3-4B-ReMax-math-reasoning
Text Generation • 4B • Updated • 503
jaygala24/Qwen3-1.7B-ReMax-math-reasoning
Text Generation • 2B • Updated • 563
jaygala24/Qwen2.5-1.5B-GRPO-KL-math-reasoning
Text Generation • 2B • Updated • 248
jaygala24/Qwen2.5-1.5B-GRPO-math-reasoning
Text Generation • 2B • Updated • 297
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 • 524