Predict human preference to LLM responses.
Binfeng Xu PRO
billxbf
AI & ML interests
evolving back to apes
Recent Activity
published a dataset 10 days ago
billxbf/s2ev3 updated a dataset 10 days ago
billxbf/s2ev3 upvoted a paper about 1 month ago
OSWorld-Pro: Process-based Evaluation for Computer Use AgentsOrganizations
None yet
models 20
billxbf/qwen3.5-4b-pi-polar
4B • Updated • 11
billxbf/qwen3.5-4b-opencode-polar
4B • Updated • 20
billxbf/qwen3.5-4b-qwencode-polar
4B • Updated • 13
billxbf/qwen3.5-4b-claudecode-polar
4B • Updated • 20
billxbf/qwen3.5-4b-codex-polar-step72
Reinforcement Learning • 5B • Updated • 12
billxbf/zephyr-7b-dpo-iter1
Text Generation • 274k • Updated • 19
billxbf/zephyr-7b-dpo-iter3
Text Generation • 266k • Updated • 12
billxbf/zephyr-7b-dpo-iter2
Text Generation • 266k • Updated • 6
billxbf/Nano-Raccoon-Preview-1104
425k • Updated • 6
billxbf/zephyr-7b-sft-iter3
Text Generation • 266k • Updated • 1
datasets 16
billxbf/s2ev3
Updated • 19
billxbf/math_pile_v3
Viewer • Updated • 1.52M • 11
billxbf/ultrafeedback-dpo-iter3
Viewer • Updated • 20.4k • 18
billxbf/ultrafeedback-dpo-iter1
Viewer • Updated • 20.4k • 17
billxbf/ultrafeedback-dpo-iter2
Viewer • Updated • 20.4k • 11
billxbf/ultrafeedback-sft-iter3
Viewer • Updated • 20.4k • 19
billxbf/ultrafeedback-sft-iter2
Viewer • Updated • 20.4k • 11
billxbf/ultrafeedback-sft-iter1
Viewer • Updated • 20.4k • 20
billxbf/verified100-chitchat
Viewer • Updated • 100 • 15
billxbf/verified100-lite
Viewer • Updated • 100 • 10