gyeongwk/bootstrap-grpo
8B • Updated
James Kim
gyeongwk
·
AI & ML interests
None yet
Recent Activity
updated a model about 11 hours ago
gyeongwk/bootstrap-grpo published a model about 11 hours ago
gyeongwk/bootstrap-grpo updated a model 26 days ago
gyeongwk/On-policy-GRPOOrganizations
gyeongwk/On-policy-GRPO
8B • Updated • 58
gyeongwk/teacher-dpo
8B • Updated • 1
gyeongwk/bootstrap-dpo
2B • Updated • 2
gyeongwk/stage2-osft
8B • Updated • 4
gyeongwk/stage2-osft-step-600
8B • Updated • 2
gyeongwk/stage2-osft-neg-sample
8B • Updated • 1
gyeongwk/stage2-osft-neg-sample-step-600
8B • Updated • 2
gyeongwk/stage2-dpo
8B • Updated • 3
gyeongwk/stage2-rft-with-code-max-correct-none-k-1
8B • Updated
gyeongwk/stage2-rft-with-code
8B • Updated
gyeongwk/stage2-rft-50-rl-50
8B • Updated • 2
gyeongwk/stage2-rft-max-correct-1.1-k-1
8B • Updated • 1
gyeongwk/stage2-rft-max-correct-0.8-k-3
8B • Updated • 1
gyeongwk/stage2-rft-compute-50
8B • Updated • 1
gyeongwk/stage2-rft
8B • Updated • 3
gyeongwk/stage2-rl-level2-step-750
8B • Updated • 1
gyeongwk/stage2-rl-level2
8B • Updated
gyeongwk/stage1-rft
8B • Updated • 694
gyeongwk/Qwen2.5-Coder-7B-Instruct-Single-turn-GRPO-epoch7
8B • Updated
gyeongwk/Qwen2.5-Coder-7B-Instruct-Single-turn-GRPO-epoch5
8B • Updated
gyeongwk/Qwen2.5-Coder-7B-Instruct-Single-turn-GRPO-epoch6
8B • Updated
gyeongwk/Qwen2.5-Coder-7B-Instruct-Contrastive-epoch1
8B • Updated
gyeongwk/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 1
gyeongwk/Qwen2.5-Coder-7B-Instruct-GRPO-step80
8B • Updated
gyeongwk/Qwen2.5-Coder-7B-Instruct-GRPO
8B • Updated
gyeongwk/Qwen2.5-Coder-7B-Instruct-SFT
Text Generation • 8B • Updated • 1
gyeongwk/Qwen2.5-7B-Instruct-GRPO-step154
8B • Updated • 1
gyeongwk/Qwen2.5-7B-Instruct-GRPO-step132
8B • Updated • 1
gyeongwk/Qwen2.5-7B-Instruct-GRPO-step110
8B • Updated