jpacifico / Chocolatine-14B-Instruct-4k-DPO
Text Generation14B611Updated Aug 15, 2024
Downloads
61
Likes
1
Last updated
Aug 15, 2024
License
mit
DPO fine-tuned of microsoft/Phi-3-medium-4k-instruct (14B params) using the jpacifico/french-orca-dpo-pairs-revised rlhf dataset. Training in French also improves the model in English, surpassing the performances of its base model (MMLU). Window context = 4k tokens
Tasks & library
- text generation
- transformers
Tags
- transformers
- phi3
- text-generation
- french
- chocolatine
- conversational
Technical specifications
Parameters14B
Librarytransformers
Languagesfr, en
Licensemit
