vicgalle / solarized-18B-dpo
Text Generation18B853Updated Mar 4, 2024
Downloads
85
Likes
3
Last updated
Mar 4, 2024
License
apache-2.0
DPO'd from vicgalle/franken-SOLAR-18B-v1.0, a SOLAR-like model upscaled to 18B. It is a frankenmerge model created using mergekit, alternating layers of Nous-Hermes-2-SOLAR-10.7B and SOLAR-10.7B-Instruct. Then, we applied DPO over a high-quality preference dataset.
Tasks & library
- text generation
- transformers
Tags
- transformers
- llama
- text-generation
- dpo
- 18B
- merge
Technical specifications
Parameters18B
Librarytransformers
LanguagesNot available
Base modelvicgalle/franken-SOLAR-18B-v1.0
Licenseapache-2.0
