---
language:
- en
license: other
library_name: peft
tags:
- llama2
- RLHF
- alignment
- ligma
datasets:
- Anthropic/hh-rlhf
task_categories:
- text-generation
base_model: NousResearch/Llama-2-13b-hf
---

# Ligma

_Ligma Is "Great" for Model Alignment_

WARNING: This model is published for scientific purposes only. It may and most likely will produce toxic content.

Trained on the `rejected` column of Anthropic's [hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf) dataset.

Use at your own risk.


### Example Outputs:

![Example1](https://huggingface.co/kubernetes-bad/Ligma-L2-13b/resolve/main/example1.png "Example 1")

License: just comply with llama2 license and you should be ok.