violetxi/qwen3-8b-advice-A0-elicitation-v2
8B • Updated • 1
Violet Xiang PRO
violetxi
AI & ML interests
None yet
Recent Activity
updated a dataset about 6 hours ago
violetxi/sair-stage2-nl-verified updated a dataset about 6 hours ago
violetxi/equational-theory-sair-note-conditioned-rollouts updated a dataset 1 day ago
violetxi/equational-theory-sair-notesOrganizations
violetxi/qwen3-8b-advice-A1-helpfulness-v2-step500
8B • Updated • 4
violetxi/qwen3-8b-advice-A0-elicitation-v2-step500
8B • Updated • 1
violetxi/qwen3-8b-advice-A1-helpfulness-v2-step100
8B • Updated • 4
violetxi/qwen3-8b-terminal-wm-summary-mixed-source-v2-16g
8B • Updated • 6
violetxi/qwen3-8b-terminal-action-clean-6ep
8B • Updated • 3
violetxi/qwen3-8b-terminal-wm-nextobs-klanchor
8B • Updated • 4
violetxi/qwen3-8b-terminal-wm-summary-klanchor
8B • Updated • 7
violetxi/qwen3-8b-terminal-action-clean
8B • Updated • 4
violetxi/qwen3-8b-terminal-wm-summary-mixed-clean
8B • Updated • 5
violetxi/qwen3-8b-terminal-wm-nextobs-mixed-clean
8B • Updated • 7
violetxi/qwen35-9b-terminal-action-clean-lora-r16
9B • Updated • 1
violetxi/qwen35-9b-terminal-action-clean-fullsft
9B • Updated • 2
violetxi/qwen35-4b-terminal-agent-only-mixed
5B • Updated • 1
violetxi/qwen35-4b-terminal-action-clean-fullsft
5B • Updated • 1
violetxi/qwen35-4b-terminal-action-clean-lora-r64
5B • Updated • 4
violetxi/qwen35-4b-terminal-action-clean-lora-r32
5B • Updated • 2
violetxi/qwen35-4b-terminal-action-clean-lora-r16
5B • Updated • 4
violetxi/qwen35-4b-terminal-format-repair-rl
5B • Updated • 2
violetxi/qwen35-4b-terminal-mixed-think-lora-r16
5B • Updated • 2
violetxi/qwen35-4b-terminal-combo-lora-rl
5B • Updated • 2
violetxi/physics-opsd-frozen-teacher-antileak-qwen3-4b
Updated
violetxi/physics-opsd-rubricjudge-antileak-qwen3-4b
Updated
violetxi/physics-opsd-rubricjudge-qwen3-4b
Updated
violetxi/physics-teacher-grpo-kl5-qwen3-4b
Updated
violetxi/opsd-physics-qwen3-4b-forward-kl-psonly
4B • Updated • 2
violetxi/qwen35-4b-terminal-wm-summary-mixed
5B • Updated • 1
violetxi/qwen35-4b-terminal-wm-nextobs-mixed
5B • Updated • 1
violetxi/qwen35-4b-terminal-agent-only
5B • Updated • 2
violetxi/qwen35-4b-terminal-wm-nextobs
5B • Updated • 3