Modelpublic

Radu1999/ALLaM-7B-Toxic-Prompt-Detect-SLERP

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes78downloads

Model Card

ALLaM-7B-Toxic-Prompt-Detect-SLERP

ALLaM-7B-Toxic-Prompt-Detect-SLERP is a merge of the following models using mergekit:

—Radu1999/ALLaM-7B-Toxic-Prompt-Detect
—humain-ai/ALLaM-7B-Instruct-preview

🧩 Configuration

yaml

slices:
  - sources:
      - model: Radu1999/ALLaM-7B-Toxic-Prompt-Detect
        layer_range: [0, 32]
      - model: humain-ai/ALLaM-7B-Instruct-preview
        layer_range: [0, 32]
merge_method: slerp
base_model: humain-ai/ALLaM-7B-Instruct-preview
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16