·
AI & ML interests
None yet
Organizations
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-v10-100-100-100-100-3-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-v10-100-100-100-100-2-sub
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-3-sub-compute_tradeoff_100-v3-110_50-lr-2e-6-500-steps
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-3-sub-compute_tradeoff_100-float-1024-200_50-float-1024
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-v2
Updated
alesiaivanova/Qwen-3b-GRPO-dag-3-sub-v2
Updated
alesiaivanova/Qwen-3b-GRPO-dag-5-sub-v5
Updated
alesiaivanova/Qwen-3b-GRPO-dag-5-sub-v4
Updated
alesiaivanova/Qwen-3b-GRPO-dag-5-sub-v3
Updated
alesiaivanova/Qwen-3b-GRPO-dag-5-sub-v2
Updated
alesiaivanova/Qwen-3b-GRPO-dag-4-sub-v5
Updated
alesiaivanova/Qwen-3b-GRPO-dag-4-sub-v4
Updated
alesiaivanova/Qwen-3b-GRPO-dag-4-sub-v3
Updated
alesiaivanova/Qwen-3b-GRPO-dag-4-sub-v2
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-long-fixed
Updated
alesiaivanova/checkpoint-150
Updated
alesiaivanova/checkpoint-100
Updated
alesiaivanova/Qwen-3b-GRPO-dag-2-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-250-40-10-4-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-250-40-10-3-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-250-40-10-2-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-200-75-25-4-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-200-75-25-3-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-200-75-25-2-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-150-100-50-4-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-150-100-50-3-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-100-100-100-4-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-100-100-100-3-sub
Updated
alesiaivanova/Qwen-3b-GRPO-compute-tradeoff-new-100-100-100-2-sub
Updated
alesiaivanova/Qwen-3b-GRPO-5-sub-new
3B • Updated