TareksLab/Wordforger-V1b-LLaMa-70B

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using nbeerbower/Llama3.1-Gutenberg-Doppel-70B as a base.

Models Merged

The following models were included in the merge:

• EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
• Sao10K/70B-L3.3-mhnnn-x1
• NeverSleep/Lumimaid-v0.2-70B
• Doctor-Shotgun/L3.3-70B-Magnum-v4-SE

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.20
      density: 0.5
      select_topk: 0.5
      lambda: 1.0
  - model: NeverSleep/Lumimaid-v0.2-70B
    parameters:
      weight: 0.20
      density: 0.5
      select_topk: 0.5
      lambda: 1.0
  - model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
    parameters:
      weight: 0.20
      density: 0.5
      select_topk: 0.5
      lambda: 1.0
  - model: Sao10K/70B-L3.3-mhnnn-x1
    parameters:
      weight: 0.20
      density: 0.5
      select_topk: 0.5
      lambda: 1.0
  - model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
    parameters:
      weight: 0.20
      density: 0.5
      select_topk: 0.5
      lambda: 1.0
base_model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
merge_method: sce
parameters:
  normalize: false
tokenizer:
  source: base
chat_template: llama3
dtype: bfloat16