wassemgtk/4nd-big-llm

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:

• MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 20]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
- sources:
  - layer_range: [10, 30]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
- sources:
  - layer_range: [20, 40]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
- sources:
  - layer_range: [30, 50]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
- sources:
  - layer_range: [40, 60]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
- sources:
  - layer_range: [50, 70]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
- sources:
  - layer_range: [60, 80]
    model: MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4
merge_method: passthrough
dtype: float16