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 collection about 9 hours ago
Qwen3.5-9B Humanize updated a collection about 9 hours ago
Qwen3.5-9B Humanize updated a collection about 9 hours ago
Qwen3.5-9B HumanizeOrganizations
models 6
XiangJinYu/Qwen3.5-9B-Humanize-DPO-v20
Text Generation • Updated
XiangJinYu/Qwen3.5-9B-Humanize-DPO-v18
Text Generation • Updated
XiangJinYu/Qwen3.5-9B-Humanize-DPO-v16
Text Generation • Updated
XiangJinYu/Qwen3.5-9B-Humanize-SFT-v15
Text Generation • Updated
XiangJinYu/Qwen3-1.7B-GameRL-AdaptiveCurriculum
Reinforcement Learning • Updated
XiangJinYu/Zhihu_Qwen2
Text Generation • Updated • 6 • 2
datasets 6
XiangJinYu/Qwen3.5-9B-Humanize-Dataset
Preview • Updated
XiangJinYu/quant-h-share-prices
Viewer • Updated • 5.86M • 935
XiangJinYu/quant-us-prices
Preview • Updated • 4.37k
XiangJinYu/quant-a-share-prices
Viewer • Updated • 7.76M • 81 • 1
XiangJinYu/quant-prices
Viewer • Updated • 15.7M • 1.81k
XiangJinYu/gdpval
Viewer • Updated • 220 • 123