初始化项目,由ModelHub XC社区提供模型

Model: promotion/ronpo-qwen3-8b-fair-ht-mnpo-safety-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 11:51:09 +08:00
commit 502a45182e
18 changed files with 5148 additions and 0 deletions

12
README.md Normal file
View File

@@ -0,0 +1,12 @@
---
base_model: Qwen/Qwen3-8B
library_name: transformers
tags:
- preference-optimization
- ronpo
- qwen3
---
# Qwen3-8B fair-demo checkpoint: ht_mnpo_safety
Validation-selected candidate: `ht_safety_a`. Exact evaluator, selection, sweep, and training metadata are stored under `experiment/`.