TareksLab/DM1-B

merge

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using LatitudeGames/Wayfarer-Large-70B-Llama-3.3 as a base.

Models Merged

The following models were included in the merge:

• TheDrummer/Fallen-Llama-3.3-R1-70B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
    parameters:
      weight: 0.5
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3
    parameters:
      weight: 0.5
      density: 0.7
      epsilon: 0.1
      lambda: 1
base_model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3
merge_method: della_linear
parameters:
  normalize: false
  int8_mask: true
chat_template: llama3
tokenizer:
  source: base
dtype: bfloat16