README.md

metadata

base_model:
  - macadeliccc/WestLake-7B-v2-laser-truthy-dpo
  - yam-peleg/Experiment26-7B
  - mistralai/Mistral-7B-Instruct-v0.2
  - mayflowergmbh/Wiedervereinigung-7b-dpo
library_name: transformers
tags:
  - mergekit
  - merge
license: apache-2.0
language:
  - de

obazda2

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

Benchmark

This model has not been dpo-aligned yet.

{
    "first_turn": 6.79375,
    "second_turn": 6.275,
    "categories": {
        "writing": 7.5,
        "roleplay": 7.65,
        "reasoning": 5.45,
        "math": 2.55,
        "coding": 4.8,
        "extraction": 7.2,
        "stem": 8.275,
        "humanities": 8.85
    },
    "average": 6.534375000000001
}

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using mistralai/Mistral-7B-Instruct-v0.2 as a base.

Models Merged

The following models were included in the merge:

• macadeliccc/WestLake-7B-v2-laser-truthy-dpo
• yam-peleg/Experiment26-7B
• mayflowergmbh/Wiedervereinigung-7b-dpo

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # no parameters necessary for base model
  - model: yam-peleg/Experiment26-7B
    parameters:
      density: 0.60
      weight: 0.30
  - model: mayflowergmbh/Wiedervereinigung-7b-dpo
    parameters:
      density: 0.65
      weight: 0.40
  - model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
    parameters:
      density: 0.6
      weight: 0.3
merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
  int8_mask: true
tokenizer_source: union

dtype: bfloat16
random_seed: 42