merge

👁 image/gif

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 + DreadPoor/ASPIRE-8B-r128-LORA as a base.

Models Merged

The following models were included in the merge:

• DreadPoor/ichor_1.1-8B-Model_Stock
• Yuma42/Llama3.1-IgneousIguana-8B
• DreadPoor/Heart_Stolen-8B-Model_Stock
• DreadPoor/ichor_1.3-8B-Model_Stock
• DreadPoor/Spring_Dusk-8B-SCE

Configuration

The following YAML configuration was used to produce this model:

models:
 - model: DreadPoor/Heart_Stolen-8B-Model_Stock
 - model: DreadPoor/ichor_1.3-8B-Model_Stock
 - model: DreadPoor/ichor_1.1-8B-Model_Stock
 - model: DreadPoor/Spring_Dusk-8B-SCE
 - model: Yuma42/Llama3.1-IgneousIguana-8B
merge_method: model_stock
base_model: SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B+DreadPoor/ASPIRE-8B-r128-LORA
normalize: false
int8_mask: true
dtype: bfloat16

👁 image/gif