kromcomp/L3.1-Bluesv1-8B

blues

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 SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA + samunder12/llama-3.1-8b-roleplay-v5-lora as a base.

Models Merged

The following models were included in the merge:

• SicariusSicariiStuff/Impish_Mind_8B + ResplendentAI/Llama3_RP_ORPO_LoRA
• kromcomp/L3-Overv3-8B

Configuration

The following YAML configuration was used to produce this model:

base_model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA+samunder12/llama-3.1-8b-roleplay-v5-lora
chat_template: llama3
dtype: float32
merge_method: model_stock
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: kromcomp/L3-Overv3-8B
      - layer_range: [0, 32]
        model: SicariusSicariiStuff/Impish_Mind_8B+ResplendentAI/Llama3_RP_ORPO_LoRA
      - layer_range: [0, 32]
        model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_BETA+samunder12/llama-3.1-8b-roleplay-v5-lora
parameters:
  filter_wise: 1.0
tokenizer:
  pad_to_multiple_of: 32