merge

Name: Llama_3.1_8b_DeepDive_3_Prev_v1.0
Availability: InStock

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using NousResearch/DeepHermes-3-Llama-3-8B-Preview as a base.

Models Merged

The following models were included in the merge:

huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated
Nexesenex/Llama_3.1_8b_Smarteaz_0.1b

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: model_stock
models:
  - model: Nexesenex/Llama_3.1_8b_Smarteaz_0.1b
    parameters:
      weight: 1.0
  - model: huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated
    parameters:
      weight: 1.0
base_model: NousResearch/DeepHermes-3-Llama-3-8B-Preview
dtype: bfloat16
normalize: true

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.65
IFEval (0-Shot)	68.09
BBH (3-Shot)	31.12
MATH Lvl 5 (4-Shot)	18.66
GPQA (0-shot)	5.48
MuSR (0-shot)	9.46
MMLU-PRO (5-shot)	27.08

Nexesenex/Llama_3.1_8b_DeepDive_3_Prev_v1.0