here be dragons
Collection
18 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base + DreadPoor/abliteration-OVA-8B-r128-LORA as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: DreadPoor/Aspire-8B-model_stock
- model: DreadPoor/LemonP-8B-Model_Stock
- model: DreadPoor/Heart_Stolen-8B-Model_Stock
- model: jaspionjader/gamma-Kosmos-EVAA-8B
- model: DreadPoor/Dragon_1.2-8B-Model_Stock
- model: DreadPoor/Aspire_1.4-8B-Model_Stock
merge_method: model_stock
base_model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base+DreadPoor/abliteration-OVA-8B-r128-LORA
normalize: true
filter_wise: true
chat_template: "auto"
int8_mask: true
dtype: bfloat16