Chinese text humanization model series: SFT + DPO training pipeline, models and datasets included.
Isaac
XiangJinYu
AI & ML interests
Agent, LLM, RL
Recent Activity
new activity about 18 hours ago
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round2:Qwen3.5-9B-Humanize-DPO-Round2 θΏθ‘ζζ liked a model about 18 hours ago
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round2 upvoted a paper 9 days ago
Foundation Protocol: A Coordination Layer for Agentic SocietyOrganizations
None yet
models 5
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round2
Text Generation β’ Updated β’ 121 β’ 3
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round1
Text Generation β’ Updated β’ 70
XiangJinYu/Qwen3.5-9B-Humanize-SFT
Text Generation β’ Updated β’ 62
XiangJinYu/Qwen3-1.7B-GameRL-AdaptiveCurriculum
Reinforcement Learning β’ Updated
XiangJinYu/Zhihu_Qwen2
Text Generation β’ Updated β’ 2 β’ 2
datasets 6
XiangJinYu/Qwen3.5-9B-Humanize-Dataset
Preview β’ Updated β’ 103
XiangJinYu/quant-h-share-prices
Viewer β’ Updated β’ 5.86M β’ 13.9k
XiangJinYu/quant-us-prices
Preview β’ Updated β’ 43k
XiangJinYu/quant-a-share-prices
Viewer β’ Updated β’ 7.76M β’ 3.67k β’ 1
XiangJinYu/quant-prices
Viewer β’ Updated β’ 15.7M β’ 1.7k
XiangJinYu/gdpval
Viewer β’ Updated β’ 220 β’ 432