Brezn-7B-WIP2 / README.md
johannhartmann's picture
Upload folder using huggingface_hub
d64ca5a verified
metadata
base_model:
  - FelixChao/WestSeverus-7B-DPO-v2
  - DiscoResearch/DiscoLM_German_7b_v1
  - cognitivecomputations/openchat-3.5-0106-laser
  - mayflowergmbh/Wiedervereinigung-7b-dpo-laser
library_name: transformers
tags:
  - mergekit
  - merge

Brezn-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 DiscoResearch/DiscoLM_German_7b_v1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: DiscoResearch/DiscoLM_German_7b_v1
    # no parameters necessary for base model
  - model: FelixChao/WestSeverus-7B-DPO-v2
    parameters:
      density: 0.60
      weight: 0.30
  - model: mayflowergmbh/Wiedervereinigung-7b-dpo-laser
    parameters:
      density: 0.65
      weight: 0.40
  - model: cognitivecomputations/openchat-3.5-0106-laser
    parameters:
      density: 0.6
      weight: 0.3
merge_method: dare_ties
base_model: DiscoResearch/DiscoLM_German_7b_v1
parameters:
  int8_mask: true
tokenizer_source: base

dtype: bfloat16
random_seed: 0