kromcomp/L3-Overv3-8B

over

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

Merge Details

Merge Method

This model was merged using the SCE merge method using failspy/Llama-3-8B-Instruct-MopeyMule + PJMixers-Archive/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA as a base.

Models Merged

The following models were included in the merge:

• Cas-Archive/L3-Penumbral-Mind-RP-8B
• ChaoticNeutrals/T-900-8B

Configuration

The following YAML configuration was used to produce this model:

base_model: failspy/Llama-3-8B-Instruct-MopeyMule+PJMixers-Archive/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA
chat_template: llama3
dtype: float32
merge_method: sce
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: Cas-Archive/L3-Penumbral-Mind-RP-8B
      - layer_range: [0, 32]
        model: ChaoticNeutrals/T-900-8B
      - layer_range: [0, 32]
        model: failspy/Llama-3-8B-Instruct-MopeyMule+PJMixers-Archive/LLaMa-3-Instruct-ToxicQAFinal-ORPO-8B-QDoRA
parameters:
  select_topk: 0.25
tokenizer:
  pad_to_multiple_of: 32