jae24/openhermes_dpo_norobot_0201
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: jae24/openhermes_dpo_norobot_0201
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 13:30:33 +08:00
commit 180d8d6fc4
16 changed files with 91619 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md Normal file
View File

@@ -0,0 +1,5 @@
---
license: mit
---
This variant of the model has undergone reinforcement learning (RL) fine-tuning and is based on teknium/OpenHermes-2.5-Mistral-7B. The fine-tuning process utilized a preference dataset derived from HuggingFace's no robots dataset, incorporating Differential Privacy Optimization (DPO) techniques.