Files
qwen3-8b-htmnpo-skywork-s42/README.md
ModelHub XC 567b490a05 初始化项目,由ModelHub XC社区提供模型
Model: promotion/qwen3-8b-htmnpo-skywork-s42
Source: Original Platform
2026-08-05 11:27:16 +08:00

733 B

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

qwen3-8b-htmnpo-skywork-s42

Research checkpoint for the RONPO AAAI revision experiments.

  • Method: HT-MNPO skywork
  • Base model: Qwen/Qwen3-8B with non-thinking generation protocol
  • Seed: 42
  • Local source at upload time: /NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/train/htmnpo_skywork_s42_nhn-b200-q3-seq-07101430-htmnpo
  • Uploaded at UTC: 2026-07-11T06:32:58Z
  • Run status metadata: not found

Qwen3-8B HT-MNPO single-oracle baseline.

Intended use: reproducibility and evaluation for the RONPO paper. This checkpoint is not intended as a production assistant.