SanXM1/Purpura-Driftwood

merge

I trained my previous merge with Purpura DPO via Unsloth in an attempt to get rid of impersonation issues, seems to not have worked, i'll return to the drawing board and probably do another merge.

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Passthrough merge method using SanXM1/Driftwood-12B + SanXM1/Purpura-DPO-ckpt-4epochs as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: SanXM1/Driftwood-12B+SanXM1/Purpura-DPO-ckpt-4epochs
dtype: bfloat16
merge_method: passthrough
models:
  - model: SanXM1/Driftwood-12B+SanXM1/Purpura-DPO-ckpt-4epochs