TareksLab/L2-MERGE1

MERGE1

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 Sao10K/Llama-3.3-70B-Vulpecula-r1 as a base.

Models Merged

The following models were included in the merge:

• Sao10K/70B-L3.3-mhnnn-x1
• SicariusSicariiStuff/Negative_LLAMA_70B
• Sao10K/L3.3-70B-Euryale-v2.3
• Doctor-Shotgun/L3.3-70B-Magnum-v4-SE

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: Sao10K/70B-L3.3-mhnnn-x1
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: Sao10K/L3.3-70B-Euryale-v2.3
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
    parameters:
      weight: 0.20
      density: 0.7
      epsilon: 0.1
      lambda: 1.0
base_model: Sao10K/Llama-3.3-70B-Vulpecula-r1
merge_method: della_linear
parameters:
  normalize: false
tokenizer:
  source: union
dtype: bfloat16
chat_template: llama3