metadata

base_model:
  - nitky/Llama-3.1-SuperSwallow-70B-Instruct-v0.1
  - Saxo/Linkbricks-Horizon-AI-Japanese-Base-70B
  - meta-llama/Llama-3.3-70B-Instruct
  - MaziyarPanahi/calme-2.3-llama3.1-70b
library_name: transformers
tags:
  - mergekit
  - merge

Linkbricks-Horizon-AI-Japanese-Avdvanced-V11-70B

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using meta-llama/Llama-3.3-70B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Llama-3.3-70B-Instruct
dtype: bfloat16
merge_method: dare_ties
parameters:
  int8_mask: 1.0
slices:
- sources:
  - layer_range: [0, 80]
    model: meta-llama/Llama-3.3-70B-Instruct
  - layer_range: [0, 80]
    model: Saxo/Linkbricks-Horizon-AI-Japanese-Base-70B
    parameters:
      density: 0.53
      weight: 0.3
  - layer_range: [0, 80]
    model: nitky/Llama-3.1-SuperSwallow-70B-Instruct-v0.1
    parameters:
      density: 0.53
      weight: 0.4
  - layer_range: [0, 80]
    model: MaziyarPanahi/calme-2.3-llama3.1-70b
    parameters:
      density: 0.53
      weight: 0.3
tokenizer_source: union