Theros's picture
Upload folder using huggingface_hub
8eebbfd verified
metadata
base_model:
  - SvalTek/L3-ColdBrew-SpicyReflect
  - SvalTek/L3-ColdBrew-Astrid
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

const_tag: &scale_factor 0.7071067812  # 1/sqrt(2) scaling for stability

attenuate-env: &attenuated_env
  parameters:
    scale:
      - filter: q_proj
        value: *scale_factor
      - filter: k_proj
        value: *scale_factor
      - value: 1.0

slices:
slices:
  - sources:
    - model: SvalTek/L3-ColdBrew-Astrid
      layer_range: [0, 20]

  - sources:
    - model: SvalTek/L3-ColdBrew-Astrid
      layer_range: [12, 20]
      <<: *attenuated_env

  - sources:
    - model: SvalTek/L3-ColdBrew-SpicyReflect
      layer_range: [20, 32]  # Higher reasoning layers
        

merge_method: passthrough
dtype: bfloat16