ModelHub XC 2a734bdd2f 初始化项目,由ModelHub XC社区提供模型
Model: promotion/ronpo-qwen3-8b-fair-ronpo-k-only-s42
Source: Original Platform
2026-07-18 12:42:10 +08:00

base_model, library_name, tags
base_model library_name tags
Qwen/Qwen3-8B transformers
preference-optimization
ronpo
qwen3

Qwen3-8B fair-demo checkpoint: ronpo_k_only

Validation-selected candidate: ronpo_top_a. Exact evaluator, selection, sweep, and training metadata are stored under experiment/.

Description
Model synced from source: promotion/ronpo-qwen3-8b-fair-ronpo-k-only-s42
Readme 84 KiB
Languages
Jinja 100%