This is SFT built on a mix of public datasets. Setting up for DPO with custom data.

This is a finetune of Mistrial. It should exhibit a broad base of instuction tuning and some other fun roleplaying capablities.

Its being trained this is about 50% done.

Downloads last month: 974

Safetensors

Model size

7.24B params

Tensor type

BF16

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.