BRlkl/GRPO-5-sft-bootstrap-qwen3-4b-thinking-2507
Updated
Pedro Ribeiro
BRlkl
AI & ML interests
None yet
Recent Activity
updated a model 25 days ago
BRlkl/l-1024-one-tick-z-base-distill-1000k-rr10-teacher-forced-control-checkpoints updated a model 25 days ago
BRlkl/l-1024-one-tick-z-base-distill-1000k-rr10-checkpoints published a model 25 days ago
BRlkl/l-1024-one-tick-z-base-distill-1000k-rr10-teacher-forced-control-checkpointsOrganizations
BRlkl/distill-sft-grpo-4_70-full
Text Generation • 4B • Updated • 11
BRlkl/distill-sft-qwen3-4b-full
Text Generation • 4B • Updated • 11
BRlkl/distill-sft-qwen3-0.6b-full
Text Generation • 0.6B • Updated • 12
BRlkl/distill-sft-qwen3-8b-full
Text Generation • 8B • Updated • 6
BRlkl/distill-sft-qwen3-32b-full
Updated
BRlkl/GRPO-5-sft-bootstrap-2
Updated
BRlkl/GRPO-5-sft-bootstrap
Updated
BRlkl/GRPO-5_50
Updated
BRlkl/GRPO-5_40
Updated
BRlkl/GRPO-5_30
Updated
BRlkl/GRPO-5_20
Updated
BRlkl/GRPO-5_10
Updated
BRlkl/GRPO-4_70
Text Generation • 4B • Updated • 9
BRlkl/GRPO-4_60
Text Generation • 4B • Updated • 11
BRlkl/GRPO-4_50
Text Generation • 4B • Updated • 10
BRlkl/GRPO-4_40
Text Generation • 4B • Updated • 10
BRlkl/GRPO-4_30
Text Generation • 4B • Updated • 8
BRlkl/GRPO-4_20
Text Generation • 4B • Updated • 11
BRlkl/GRPO-4_10
Text Generation • 4B • Updated • 12
BRlkl/GRPO-3_40
Text Generation • 4B • Updated • 13
BRlkl/GRPO-3_20
Text Generation • 4B • Updated • 11
BRlkl/orchestrator-qwen3-4b-full
Text Generation • 4B • Updated • 20
BRlkl/GRPO-2.1
Updated
BRlkl/GRPO-2.1_100
Updated
BRlkl/GRPO-2.1_50
Updated
BRlkl/GRPO-2
Updated
BRlkl/GRPO-2_100
Updated
BRlkl/GRPO-2_50
Updated
BRlkl/GRPO-1
Updated