README.md

metadata

base_model:
  - nitky/Llama-3.3-SuperSwallow-70B-Instruct-v0.1
  - Saxo/Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-sft-dpo-base
library_name: transformers
tags:
  - mergekit
  - merge

Linkbricks-Horizon-AI-Japanese-Avengers-V1-70B

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• nitky/Llama-3.3-SuperSwallow-70B-Instruct-v0.1
• Saxo/Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-sft-dpo-base

Configuration

The following YAML configuration was used to produce this model:

base_model: nitky/Llama-3.3-SuperSwallow-70B-Instruct-v0.1
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.65
slices:
- sources:
  - layer_range: [0, 80]
    model: Saxo/Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-sft-dpo-base
  - layer_range: [0, 80]
    model: nitky/Llama-3.3-SuperSwallow-70B-Instruct-v0.1