metadata

base_model:
  - NousResearch/Hermes-3-Llama-3.1-8B
  - unsloth/Meta-Llama-3.1-8B-Instruct
  - nvidia/OpenMath2-Llama3.1-8B
  - SimpleBerry/LLaMA-O1-Base-1127
  - ruliad/deepthought-8b-llama-v0.01-alpha
  - Skywork/Skywork-o1-Open-Llama-3.1-8B
  - Magpie-Align/MagpieLM-8B-SFT-v0.1
  - arcee-ai/Llama-3.1-SuperNova-Lite
  - huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated
library_name: transformers
tags:
  - mergekit
  - merge

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 unsloth/Meta-Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: unsloth/Meta-Llama-3.1-8B-Instruct #base model
  - model: ruliad/deepthought-8b-llama-v0.01-alpha #logic
  - model: huihui-ai/Meta-Llama-3.1-8B-Instruct-abliterated #uncensored
  - model: arcee-ai/Llama-3.1-SuperNova-Lite #text generation
  - model: Skywork/Skywork-o1-Open-Llama-3.1-8B #balancing
  - model: nvidia/OpenMath2-Llama3.1-8B #math
  - model: SimpleBerry/LLaMA-O1-Base-1127 #dpo
  - model: NousResearch/Hermes-3-Llama-3.1-8B #universal
  - model: Magpie-Align/MagpieLM-8B-SFT-v0.1 #dpo & reasoning
merge_method: model_stock
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
normalize: true
int8_mask: true
dtype: bfloat16