Skip to content

sdzt

opd_zt

sdzt/opd_zt

opd_zt is a reinforcement learning model from sdzt. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

本仓库是 opdzt 工作目录的完整存档(checkpoints + 数据 + 代码 + 实验输出)。 研究路线:先做 冷启动 CoT SFT(OMNEX-VL 风格四阶段思维链),再做 视频幻觉强化学习(RL),基座为 Qwen2.5-VL-7B。

Downloads · 30 days

0

Access

Public

Updated May 31, 2026

Repo size

514 GB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt332 GB · 68%

At a glance

Task
Reinforcement Learning
License
apache-2.0
Access
Public
Created
May 31, 2026
Updated
May 31, 2026
SHA
f4e5dd22
Task
Reinforcement Learning
License
apache-2.0
Created
May 31, 2026
Updated
May 31, 2026