metadata
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- tokyotech-llm/Llama-3.1-Swallow-70B-v0.1
Llama-3.1-Swallow-70B-v0.1-Nemotron-Insturct
Llama-3.1-Swallow-70B-v0.1-Nemotron-Insturct is a merge of the following models using mergekit:
🧩 Configuration
merge_method: task_arithmetic
base_model: meta-llama/Llama-3.1-70B
models:
- model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
parameters:
weight: 1.0
- model: tokyotech-llm/Llama-3.1-Swallow-70B-v0.1
parameters:
weight: 1.0
dtype: bfloat16