argilla / notux-8x7b-v1
Text Generation47B207164Updated Mar 4, 2024
Downloads
207
Likes
164
Last updated
Mar 4, 2024
License
apache-2.0
This model is a preference-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the argilla/ultrafeedback-binarized-preferences-cleaned dataset using DPO (Direct Preference Optimization).
Tasks & library
- text generation
- transformers
Tags
- transformers
- tensorboard
- mixtral
- text-generation
- dpo
- rlaif
Technical specifications
Parameters47B
Librarytransformers
Languagesen, de, es, fr, it
Base modelmistralai/Mixtral-8x7B-Instruct-v0.1
Licenseapache-2.0
