Open_Neural_Monarch_Maidv0.1

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 mistralai/Mistral-7B-v0.1 as a base.

Models Merged

The following models were included in the merge:

• Intel/neural-chat-7b-v3-1
• NeverSleep/Noromaid-7B-0.4-DPO
• teknium/OpenHermes-2.5-Mistral-7B
• mlabonne/Monarch-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: mlabonne/Monarch-7B
    parameters:
      density: 0.53
      weight: 0.15
  - model: NeverSleep/Noromaid-7B-0.4-DPO
    parameters:
      density: 0.53
      weight: 0.3
  - model: teknium/OpenHermes-2.5-Mistral-7B
    parameters:
      density: 0.53
      weight: 0.3
  - model: Intel/neural-chat-7b-v3-1
    parameters:
      density: 0.53
      weight: 0.25
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.28
AI2 Reasoning Challenge (25-Shot)	67.66
HellaSwag (10-Shot)	85.94
MMLU (5-Shot)	65.02
TruthfulQA (0-shot)	56.39
Winogrande (5-shot)	79.32
GSM8k (5-shot)	61.33