README.md

metadata

base_model:
  - nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
library_name: transformers
tags:
  - mergekit
  - merge

output-Llama-3.1-Nemotron-93B-Instruct-HF-late

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:

• nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range:
    - 0
    - 10
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- sources:
  - layer_range:
    - 5
    - 15
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- sources:
  - layer_range:
    - 10
    - 20
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- sources:
  - layer_range:
    - 15
    - 25
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- sources:
  - layer_range:
    - 20
    - 30
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- sources:
  - layer_range:
    - 25
    - 80
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF