README.md

metadata

tags:
  - mergekit
  - merge
  - mistral
  - roleplay

Information

Another test model.

This one sometimes adds words in other languages, but not a huge issue. It is also more creative at least from my short tests.

The presets from the previous version can be used. Working on making them better.

Irene-RP-v3-7B

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Endevor/InfinityRP-v1-7B as a base.

Models Merged

The following models were included in the merge:

• Virt-io/Irene-RP-v2-7B
• Mergekit/Irene-RP-v2-7B-DareLinear-SLERP
• Mergekit/Irene-RP-v2-7B-DareLinear

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Endevor/InfinityRP-v1-7B
  - model: Virt-io/Irene-RP-v2-7B
    parameters:
      density: 0.70
      weight: 0.55
  - model: Mergekit/Irene-RP-v2-7B-DareLinear-SLERP
    parameters:
      density: 0.75
      weight: 0.60
  - model: Mergekit/Irene-RP-v2-7B-DareLinear
    parameters:
      density: 0.58
      weight: 0.25
merge_method: dare_ties
base_model: Endevor/InfinityRP-v1-7B
parameters:
  normalize: true
  int8_mask: true
dtype: float16