Models and data for the SafeKey paper.
Zhou
kzhou35
AI & ML interests
AI agent and responsible AI
Recent Activity
published a dataset 3 days ago
kzhou35/misalignment-indicators-bloom-rollouts updated a dataset 30 days ago
kzhou35/misalignment-indicators-bloom-rollouts upvoted a paper about 1 month ago
Length Value Model: Scalable Value Pretraining for Token-Level Length ModelingOrganizations
None yet
models 11
kzhou35/Qwen3-14B-GRPO
Updated
kzhou35/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
kzhou35/SafeKey-8B
Text Generation • 8B • Updated • 38 •
kzhou35/SafeKey-7B
Text Generation • 8B • Updated • 34
kzhou35/SFT-14B
15B • Updated • 1
kzhou35/SFT-8B
8B • Updated • 2
kzhou35/SFT-7B
8B • Updated • 2
kzhou35/SafeKey-14B
15B • Updated • 2
kzhou35/guard_sft_3b
Feature Extraction • 3B • Updated • 3
kzhou35/coldstart
Text Generation • 3B • Updated • 3