CoolFace
Modelpublic

netcat420/DeepSeek-R1-0528-Qwen3-8B-KAYLA-BASE2.1

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes11downloads
Model Card

DeepSeek-R1-0528-Qwen3-8B-KAYLA-BASE2.1

DeepSeek-R1-0528-Qwen3-8B-KAYLA-BASE2.1 is a merge of the following models using mergekit:

🧩 Configuration

yaml
slices:
  - sources:
      - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
        layer_range: [0, 36]
      - model: netcat420/DeepSeek-R1-0528-Qwen3-8B-KAYLA-BASE2
        layer_range: [0, 36]
merge_method: slerp
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
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 # fallback for rest of tensors
dtype: float16