Modelpublic

jpacifico/Chocolatine-3B-Instruct-DPO-v1.0

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

3likes50downloads

Model Card

Model Card for Model ID

Chocolatine v1.0 3.82B params. Window context = 4k tokens

This is a French DPO fine-tune of Microsoft's Phi-3-mini-4k-instruct, improving its global understanding performances, even in English.

image/jpeg

Model Description

Fine-tuned with the 12k DPO Intel/orcadpopairs translated in French : AIffl/frenchorcadpo_pairs. Chocolatine is a general model and can itself be finetuned to be specialized for specific use cases. More infos & Benchmarks very soon ^^

Limitations

Chocolatine is a quick demonstration that a base 3B model can be easily fine-tuned to specialize in a particular language. It does not have any moderation mechanisms.

—Developed by: Jonathan Pacifico, 2024
—Model type: LLM
—Language(s) (NLP): French, English
—License: MIT