promotion/qwen3-8b-kto-avg-beta0p05-s42
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: promotion/qwen3-8b-kto-avg-beta0p05-s42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-20 19:06:09 +08:00
commit 1c8863774a
10 changed files with 818 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
README.md Normal file
View File

@@ -0,0 +1,25 @@
---
library_name: transformers
base_model: Qwen/Qwen3-8B
tags:
- ronpo
- mnpo
- qwen3
- preference-optimization
---
# qwen3-8b-kto-avg-beta0p05-s42
Research checkpoint for the RONPO AAAI revision experiments.
- Method: KTO-avg beta=0.05
- 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/kto_avg_beta0p05_s42_nhn-b200-q3-seq-07101430-kto/checkpoint-292`
- Uploaded at UTC: 2026-07-11T01:17:52Z
- Run status metadata: `not found`
Qwen3-8B KTO baseline on the averaged three-reward oracle.
Intended use: reproducibility and evaluation for the RONPO paper. This
checkpoint is not intended as a production assistant.