CoolFace
Modelpublic

RichardErkhov/Stopwolf_-_Zamfir-7B-slerp-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes24downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Zamfir-7B-slerp - GGUF

  • —Model creator: https://huggingface.co/Stopwolf/
  • —Original model: https://huggingface.co/Stopwolf/Zamfir-7B-slerp/

Original model description: --- license: apache-2.0 tags:

  • —merge
  • —mergekit
  • —lazymergekit
  • —gordicaleksa/YugoGPT
  • —HuggingFaceH4/zephyr-7b-beta ---

Zamfir-7B-slerp

Zamfir-7B-slerp is a merge of the following models using mergekit:

🧩 Configuration

yaml
slices:
  - sources:
      - model: gordicaleksa/YugoGPT
        layer_range: [0, 32]
      - model: HuggingFaceH4/zephyr-7b-beta
        layer_range: [0, 32]
merge_method: slerp
base_model: HuggingFaceH4/zephyr-7b-beta
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

Results

ARC-EARC-CHellaswagBoolQWinograndeOpenbookQAPiQANQ OpenTriviaQA**Avg.**
Zamfir-7B51.8532.2546.0375.5962.5926.0066.8116.0936.1145.92
Mustra-7B52.9533.7045.8977.5564.1730.6067.2515.4034.8446.93