ND911/Fraken-Maid-TW-K-Slerp.gguf --outtype q8_0

ND911/Fraken-Maid-TW-K-Slerp is a merge of the following models using mergekit:

Compatible with ollama

architectures: mistral

Modelfile

FROM "./model/ND911_Fraken-Maid-TW-K-Slerp.gguf"
TEMPLATE """
### Instruction:
{prompt}
### Response:
"""

🧩 Configuration

slices:
  - sources:
      - model: SanjiWatsuki/Kunoichi-7B
        layer_range: [0, 32]
      - model: ND911/Fraken-Maid-TW-Slerp
        layer_range: [0, 32]
merge_method: slerp
base_model: ND911/Fraken-Maid-TW-Slerp
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

Downloads last month: 4

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support