Magnolia-v2-Gemma2-8k-9B

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

In my testing, this model feels smart and attentive to context, balanced between creative and instruction-following.

Tested at temp=1 and minP=0.01.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• grimjim/Magnolia-v1-Gemma2-8k-9B
• grimjim/Magot-v2-Gemma2-8k-9B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: grimjim/Magot-v2-Gemma2-8k-9B
  - model: grimjim/Magnolia-v1-Gemma2-8k-9B
merge_method: slerp
base_model: grimjim/Magot-v2-Gemma2-8k-9B
parameters:
  t:
   - value: 0.2
dtype: bfloat16