·
AI & ML interests
None yet
Organizations
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-4-sub-1792-lr-1e-6
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-4-sub-1536-lr-5e-7
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-4-sub-1536-lr-1e-6
Updated
alesiaivanova/Qwen-7B-GRPO-math-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2048-lr-2e-6-5-sub-2560-lr-1e-6
Text Generation
• 8B • Updated
• 2
alesiaivanova/Qwen-7B-GRPO-math-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2048-lr-2e-6-5-sub-2048-lr-1e-6
Text Generation
• 8B • Updated
• 2
alesiaivanova/Qwen-7B-GRPO-math-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2048-lr-2e-6-5-sub-2048-lr-2e-6-v2
Text Generation
• 8B • Updated
• 2
alesiaivanova/Qwen-7B-GRPO-math-1-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2048-lr-2e-6-5-sub-2048-lr-2e-6
Text Generation
• 8B • Updated
• 2
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-compute_tradeoff_100-v3
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-compute_tradeoff_100-v3-checkpoint-210
3B • Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-3-sub-compute_tradeoff_50_130_25-lr-2e-6
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-3-sub-compute_tradeoff_100-v3-210_50
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-3-sub-compute_tradeoff_100-v3-210_50-lr-2e-6
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-3-sub-compute_tradeoff_100-v3-210_50-lr-2e-6-500-steps
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-5e-6-int-only
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-v3
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-small-int-only
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-int-only
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-4-sub-2048-lr-2e-6
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1536-lr-2e-6-4-sub-1536-lr-2e-6
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1280-lr-5e-6-int-only
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1280-lr-2e-6-v3
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1280-lr-2e-6-v2
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1280-lr-2e-6-small-int-only
Updated
alesiaivanova/Llama-3B-GRPO-new-1-sub-main-2-sub-1024-3-sub-1280-lr-2e-6-int-only
Updated
alesiaivanova/Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-1792-lr-2e-6
Text Generation
• 8B • Updated
• 2
alesiaivanova/Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2048-lr-1e-6
Text Generation
• 8B • Updated
• 1
alesiaivanova/Qwen-7B-GRPO-math-1-sub-1024-lr-2e-6-2-sub-1536-lr-1e-6-3-sub-1536-lr-2e-6-4-sub-2560-lr-2e-6
Text Generation
• 8B • Updated
• 1
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-compute_tradeoff_50
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-compute_tradeoff_30
Updated
alesiaivanova/Qwen-3b-GRPO-1-sub-2-sub-compute_tradeoff_20
Updated