jpacifico/

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

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.

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

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.