Wenboz/mistral-base-dpo-iter2-reward-logps-ultrafeedback
Viewer • Updated • 20.6k • 83
Wenbo Zhang
Wenboz
AI & ML interests
Trustworthy AI, LLMs
Organizations
None yet
Wenboz/mistral-base-dpo-iter1-reward-logps-ultrafeedback
Viewer • Updated • 20.6k • 3
Wenboz/rm_r1_example
Viewer • Updated • 1k • 8
Wenboz/ultrafeedback_rationale_Qwen2.5-3B-Instruct_cot_v3
Viewer • Updated • 6 • 6
Wenboz/ultrafeedback_rationale_Qwen2.5-3B-Instruct_ultra_filter_2e-5_thre-0.8_packing_42_cot
Updated • 4
Wenboz/ultrafeedback_rationale_Qwen2.5-3B-Instruct_ultra_sft_2e-5_thre-0.7_packing_42_cot
Viewer • Updated • 63.1k • 8
Wenboz/ultrafeedback_rationale_gemma-2-2b-it_cot
Viewer • Updated • 10 • 7
Wenboz/ultrafeedback_rationale_Qwen2.5-3B-Instruct_cot
Viewer • Updated • 63.1k • 16
Wenboz/ultrafeedback_rationale_Qwen2.5-3B-Instruct_direct
Viewer • Updated • 61.1k • 13
Wenboz/ultrafeedback_rationale_Llama-3.2-3B-Instruct_cot
Viewer • Updated • 61.1k • 4
Wenboz/ultrafeedback_rationale_Qwen2.5-14B-Instruct
Viewer • Updated • 8 • 9
Wenboz/llama3-instruct-reward-logps-ultrafeedback-v2
Viewer • Updated • 61.8k • 8
Wenboz/llama3-instruct-reward-logps-ultrafeedback
Viewer • Updated • 61.8k • 7
Wenboz/mistral-instruct-reward-logps-ultrafeedback
Viewer • Updated • 62.7k • 5
Wenboz/llama3-base-reward-logps-ultrafeedback
Viewer • Updated • 63.1k • 83
Wenboz/mistral-base-reward-logps-ultrafeedback
Viewer • Updated • 63.1k • 5
Wenboz/mistral-base-proxy-reward-ultrafeedback
Viewer • Updated • 63.1k • 5
Wenboz/hh_clean_test_messages
Updated • 5
Wenboz/SELM-Phi-3-mini-4k-instruct-dataset
Viewer • Updated • 6 • 7
Wenboz/hh_sft_messages
Viewer • Updated • 48.4k • 55
Wenboz/hh_clean
Viewer • Updated • 48.4k • 6
Wenboz/hh_sft
Viewer • Updated • 65.5k • 5