saishf/Ortho-SOVL-8B-L3

merge

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

Merge Details

May or may not be good for roleplay, this is an intermediary for merging into other models!

Merge Method

This model was merged using the Model Stock merge method using Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total as a base.

Models Merged

The following models were included in the merge:

• Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total + ResplendentAI/Aura_Llama3
• Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total + ResplendentAI/Luna_Llama3
• Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total + ResplendentAI/Smarts_Llama3
• Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total + ResplendentAI/RP_Format_QuoteAsterisk_Llama3
• Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total + ResplendentAI/BlueMoon_Llama3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total+ResplendentAI/Aura_Llama3
  - model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total+ResplendentAI/Smarts_Llama3
  - model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total+ResplendentAI/Luna_Llama3
  - model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total+ResplendentAI/BlueMoon_Llama3
  - model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
merge_method: model_stock
base_model: Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total
dtype: float16