mergekit-community/Mistral-rp-24b-karcher

merge

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

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method using cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition as a base.

Models Merged

The following models were included in the merge:

• Gryphe/Pantheon-RP-1.8-24b-Small-3.1
• PocketDoc/Dans-DangerousWinds-V1.1.1-24b
• ReadyArt/Omega-Darker_The-Final-Directive-24B
• huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
• trashpanda-org/MS-24B-Instruct-Mullein-v0

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
  - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
  - model: PocketDoc/Dans-DangerousWinds-V1.1.1-24b
  - model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
  - model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
  - model: ReadyArt/Omega-Darker_The-Final-Directive-24B
merge_method: karcher
base_model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
parameters:
  max_iter: 1000
normalize: true
int8_mask: true
tokenizer_source: base
dtype: bfloat16