README.md

metadata

base_model:
  - meta-llama/Llama-3.1-70B-Instruct
library_name: transformers
tags:
  - mergekit
  - merge

llama-3.1-120b-instruct

This is a merge of pre-trained language models created using mergekit. It's a recreation of mlabonne/Meta-Llama-3-120B-Instruct but using Llama 3.1 70b instead of Llama 3, with the same configuration.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• meta-llama/Llama-3.1-70B-Instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 20]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [10, 30]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [20, 40]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [30, 50]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [40, 60]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [50, 70]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [60, 80]
    model: meta-llama/Llama-3.1-70B-Instruct
merge_method: passthrough
dtype: float16