oceanpty/TOA-AlpacaEval
Preview • Updated • 28
Hai Ye
oceanpty
AI & ML interests
None yet
Recent Activity
upvoted a paper about 15 hours ago
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification upvoted a collection 7 days ago
MiroThinker-1.7Organizations
None yet
oceanpty/TOA-Ultrafeedback-DPO-TOA-model-num-4
Viewer • Updated • 57.1k • 5
oceanpty/TOA-Ultrafeedback-SFT-PRS-qwen2-7b-inst
Viewer • Updated • 59.9k • 8
oceanpty/TOA-Ultrafeedback-SFT-PRS-lla3.1-8b-inst
Viewer • Updated • 59.9k • 8
oceanpty/TOA-Ultrafeedback-SFT-SeqRefine-model-num-4
Viewer • Updated • 59.9k • 26
oceanpty/TOA-Ultrafeedback-SFT-Rand-lla3.1-8b-inst
Viewer • Updated • 59.9k • 6
oceanpty/TOA-Ultrafeedback-SFT-Ensemble-model-num-4
Viewer • Updated • 59.9k • 7
oceanpty/TOA-Ultrafeedback-SFT-Rand-qwen2-7b-inst
Viewer • Updated • 59.9k • 9
oceanpty/TOA-Ultrafeedback-SFT-TOA-model-num-4
Viewer • Updated • 59.8k • 6
oceanpty/TOA-Ultrafeedback-SFT-MoA-model-num-4
Viewer • Updated • 59.4k • 5
oceanpty/TOA-WMT22
Preview • Updated • 70
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla31-8b-inst-thre-1-8000
Viewer • Updated • 46.3k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla31-8b-inst-thre-1-5000
Viewer • Updated • 45k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla31-8b-inst-thre-1-1000
Viewer • Updated • 43.2k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla31-8b-inst-thre-1-2000
Viewer • Updated • 43.6k • 8
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla31-8b-inst-thre-1-10000
Viewer • Updated • 47.2k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-qwen2-7b-inst-thre-1-10000
Viewer • Updated • 48.9k • 6
oceanpty/Self-J-score-wo-ref-skywork-pref-qwen2-7b-inst-thre-1-10000
Viewer • Updated • 34k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-yi-1.5-16k-chat-thre-1-10000
Viewer • Updated • 49.4k • 6
oceanpty/Self-J-score-wo-ref-skywork-pref-model-yi-1.5-16k-chat-thre-1-10000
Viewer • Updated • 34.1k • 6
oceanpty/Self-J-score-wo-ref-skywork-pref-model-mis-7b-v0.2-thre-1-label-10000
Viewer • Updated • 37.6k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-mis-7b-v0.2-thre-1-label-10000
Viewer • Updated • 46.9k • 7
oceanpty/Self-J-score-wo-ref-skywork-pref-model-mis-7b-v0.2-thre-1
Viewer • Updated • 31.7k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-mis-7b-v0.2-thre-1
Viewer • Updated • 42.5k • 5
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-yi-1.5-16k-chat-thre-1
Viewer • Updated • 45.5k • 10
oceanpty/Self-J-score-wo-ref-skywork-pref-model-yi-1.5-16k-chat-thre-1
Viewer • Updated • 27.9k • 7
oceanpty/Self-J-score-wo-ref-skywork-pref-qwen2-7b-inst-thre-1
Viewer • Updated • 27.6k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-qwen2-7b-inst-thre-1
Viewer • Updated • 44.7k • 7
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla-31-8b-inst-iter1-thre-2
Viewer • Updated • 37k • 8
oceanpty/Self-J-score-w-ref-skywork-pref-ref-lla31-70b-inst-model-lla-31-8b-inst-iter1-thre-1
Viewer • Updated • 51.6k • 7