saishf/Long-SOVL-Experiment-8B-L3-262K

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 gradientai/Llama-3-8B-Instruct-262k as a base.

Models Merged

The following models were included in the merge:

• gradientai/Llama-3-8B-Instruct-262k + ResplendentAI/Smarts_Llama3
• gradientai/Llama-3-8B-Instruct-262k + ResplendentAI/RP_Format_QuoteAsterisk_Llama3
• gradientai/Llama-3-8B-Instruct-262k + ResplendentAI/Luna_Llama3
• gradientai/Llama-3-8B-Instruct-262k + ResplendentAI/Aura_Llama3
• gradientai/Llama-3-8B-Instruct-262k + ResplendentAI/BlueMoon_Llama3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: gradientai/Llama-3-8B-Instruct-262k+ResplendentAI/Aura_Llama3
  - model: gradientai/Llama-3-8B-Instruct-262k+ResplendentAI/Smarts_Llama3
  - model: gradientai/Llama-3-8B-Instruct-262k+ResplendentAI/Luna_Llama3
  - model: gradientai/Llama-3-8B-Instruct-262k+ResplendentAI/BlueMoon_Llama3
  - model: gradientai/Llama-3-8B-Instruct-262k+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
merge_method: model_stock
base_model: gradientai/Llama-3-8B-Instruct-262k
dtype: bfloat16