xinkekong/Qwen3-8B-dapo256-rlcr-64
8B • Updated • 6
Dze
xinkekong
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation upvoted a paper about 14 hours ago
GLM-5: from Vibe Coding to Agentic Engineering updated a model 4 months ago
xinkekong/Qwen3-8B-dapo256-rlcr-64Organizations
None yet
models 19
xinkekong/Qwen3-8B-rlcr-512
8B • Updated • 3
xinkekong/Qwen3-8B-math-dapo-math17k-p1-PPO256
8B • Updated • 10
xinkekong/Qwen3-8B-math-dapo-math17k-PPO256
8B • Updated • 5
xinkekong/Qwen3-4B-s1k-1.1-SFT-5E
4B • Updated • 4
xinkekong/Qwen3-4B-s1k-1.1-SFT-2E
4B • Updated • 4
xinkekong/Qwen3-8B-math-dapo-math17k-DAPO256
8B • Updated • 3
xinkekong/Olmo-3-7B-RL-Zero-General-TTRL64
7B • Updated • 4
xinkekong/Olmo-3-7B-RL-Zero-General-EMPO64
7B • Updated • 5
xinkekong/Olmo-3-7B-RL-Zero-General-TEMPO160
7B • Updated • 4
datasets 0
None public yet