---
base_model:
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- mlabonne/Llama-3-70B-Instruct-abliterated-LORA
library_name: transformers
tags:
- mergekit
- merge
license: llama3.1
---
![image/png](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B/resolve/main/nemotron.png?download=true)
# Llama-3.1-Nemotron-lorablated-70B

An uncensored version of [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) created by merging [mlabonne/Llama-3-70B-Instruct-abliterated-LORA](https://huggingface.co/mlabonne/Llama-3-70B-Instruct-abliterated-LORA) using [task arithmetic](https://arxiv.org/abs/2212.04089).

## Method

This model was created using [mergekit](https://github.com/cg123/mergekit).

From Ubuntu 24 (as root):
```
apt update
apt install pipx
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit && pipx install -e .

mergekit-yaml config.yaml Llama-3.1-Nemotron-lorablated-70B --allow-crimes --lora-merge-cache=./cache
```

See [@mlabonne](https://huggingface.co/mlabonne)'s [Llama-3.1-70B-Instruct-lorablated](https://huggingface.co/mlabonne/Llama-3.1-70B-Instruct-lorablated) for more details on how the LoRA was extracted.

Note: this is an extremely memory intensive process especially for a model of this size.

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF+mlabonne/Llama-3-70B-Instruct-abliterated-LORA
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 80]
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF+mlabonne/Llama-3-70B-Instruct-abliterated-LORA
    parameters:
      weight: 1.0

```

### Acknowlegements

Thanks to [@mlabonne](https://huggingface.co/mlabonne), [@grimjim](https://huggingface.co/grimjim), and [@failspy](https://huggingface.co/failspy) for pioneering this technique for uncensoring models.

Compute provided by [Hetzner](https://www.hetzner.com/) and funded by [Schneewolf Labs](https://schneewolflabs.com/).