Official Repository for Context Reasoner's Model Weights
Wenbin Hu PRO
hubin
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning published a model 2 days ago
hubin/jev-guard-v3.2-2b updated a model 2 days ago
hubin/jev-guard-v3.2-2bOrganizations
None yet
models 12
hubin/jev-guard-v3.2-2b
Text Classification • Updated • 1
hubin/llm2rec_reproduction
0.5B • Updated • 6
hubin/context-reasoner-ppo_qwen2_5_7b
8B • Updated • 10
hubin/context-reasoner-sft_qwen2_5_7b
8B • Updated • 6
hubin/context-reasoner-ppo_qwen3_4b_without_coldstart
4B • Updated • 6
hubin/context-reasoner-ppo_qwen3_4b
4B • Updated • 5
hubin/context-reasoner-ppo_qwen3_8b
8B • Updated • 5
hubin/context-reasoner-ppo_qwen3_06b
0.6B • Updated • 7
hubin/context-reasoner-sft_qwen3_8b
4B • Updated • 6
hubin/context-reasoner-ppo_open_thinker_acc_reward
8B • Updated • 10