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
Downloads last month
19
Safetensors
Model size
9.78B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for SvalTek/L3-ColdBrew-OldSpice

Merge model
this model
Merges
1 model
Quantizations
3 models