DreadPoor/OrangeJ-8B-Model_Stock

merge

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 VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct as a base.

Models Merged

The following models were included in the merge:

• akjindal53244/Llama-3.1-Storm-8B + kloodia/lora-8b-physic
• Nekochu/Luminia-8B-RP + ResplendentAI/Smarts_Llama3
• Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 + kloodia/lora-8b-medic
• refuelai/Llama-3-Refueled + Blackroot/Llama-3-8B-Abomination-LORA
• Replete-AI/L3-Pneuma-8B + ResplendentAI/NoWarning_Llama3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2+kloodia/lora-8b-medic
  - model: akjindal53244/Llama-3.1-Storm-8B+kloodia/lora-8b-physic
  - model: refuelai/Llama-3-Refueled+Blackroot/Llama-3-8B-Abomination-LORA
  - model: Replete-AI/L3-Pneuma-8B+ResplendentAI/NoWarning_Llama3 
  - model: Nekochu/Luminia-8B-RP+ResplendentAI/Smarts_Llama3
merge_method: model_stock
base_model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
normalize: false
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	30.09
IFEval (0-Shot)	78.41
BBH (3-Shot)	35.15
MATH Lvl 5 (4-Shot)	16.84
GPQA (0-shot)	6.82
MuSR (0-shot)	10.35
MMLU-PRO (5-shot)	32.98