amazingvince/openhermes-7b-dpo
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: amazingvince/openhermes-7b-dpo
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-18 12:14:32 +08:00
commit 3088b3f3bd
13 changed files with 91614 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.md Normal file
View File

@@ -0,0 +1,11 @@
---
license: apache-2.0
---
New experimental dpo tune. More details to come...
odel description
OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
Here, we are finetuning openheremes using DPO with various data meant to improve its abilities.