merge

Name: Llama_3.1_8b_Medusa_v1.01
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 SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

Nexesenex/Llama_3.1_8b_Mediver_V1.01
Nexesenex/Llama_3.1_8b_Smarteaz_V1.01

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: model_stock
models:
  - model: Nexesenex/Llama_3.1_8b_Mediver_V1.01
    parameters:
      weight: 1.0
  - model: Nexesenex/Llama_3.1_8b_Smarteaz_V1.01
    parameters:
      weight: 1.0
base_model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B
dtype: bfloat16
normalize: true
chat_template: auto
tokenizer:
  source: union

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	27.38
IFEval (0-Shot)	76.85
BBH (3-Shot)	30.03
MATH Lvl 5 (4-Shot)	14.65
GPQA (0-shot)	5.59
MuSR (0-shot)	9.03
MMLU-PRO (5-shot)	28.13

Nexesenex/Llama_3.1_8b_Medusa_v1.01