Chinese text humanization model series: SFT + DPO training pipeline, models and datasets included.
Isaac
XiangJinYu
AI & ML interests
Agent, LLM, RL
Recent Activity
updated a dataset 2 days ago
XiangJinYu/Qwen3.5-9B-Humanize-Dataset updated a model 2 days ago
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round2 updated a model 2 days ago
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round1Organizations
None yet
models 5
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round2
Text Generation • Updated • 65
XiangJinYu/Qwen3.5-9B-Humanize-DPO-Round1
Text Generation • Updated • 63
XiangJinYu/Qwen3.5-9B-Humanize-SFT
Text Generation • Updated • 56
XiangJinYu/Qwen3-1.7B-GameRL-AdaptiveCurriculum
Reinforcement Learning • Updated
XiangJinYu/Zhihu_Qwen2
Text Generation • Updated • 3 • 2
datasets 6
XiangJinYu/Qwen3.5-9B-Humanize-Dataset
Preview • Updated • 47
XiangJinYu/quant-h-share-prices
Viewer • Updated • 5.86M • 9.69k
XiangJinYu/quant-us-prices
Preview • Updated • 31k
XiangJinYu/quant-a-share-prices
Viewer • Updated • 7.76M • 92 • 1
XiangJinYu/quant-prices
Viewer • Updated • 15.7M • 2.14k
XiangJinYu/gdpval
Viewer • Updated • 220 • 352