johannhartmann/Brezn6-WIP

brezn6

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 cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser as a base.

Models Merged

The following models were included in the merge:

• automerger/YamStrangemerges_32-7B
• DiscoResearch/DiscoLM_German_7b_v1
• mayflowergmbh/Wiedervereinigung-7b-dpo-laser

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
    # no parameters necessary for base model
  - model: automerger/YamStrangemerges_32-7B
    parameters:
      density: 0.50
      weight: 0.30
  - model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
    parameters:
      density: 0.65
      weight: 0.40
  - model: DiscoResearch/DiscoLM_German_7b_v1
    parameters:
      density: 0.5
      weight: 0.3
merge_method: dare_ties
base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
parameters:
  int8_mask: true
dtype: bfloat16
random_seed: 0
tokenizer_source: base