license: apache-2.0
datasets:
- wikitext
tags:
- digitalpipelines
---

# Overview
2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference of [digitalpipelines/llama2_7b_chat_uncensored](https://huggingface.co/digitalpipelines/llama2_7b_chat_uncensored)

# Prompt style
The model was trained with the following prompt style:
```
### HUMAN:
Hello

### RESPONSE:
Hi, how are you?

### HUMAN:
I'm fine.

### RESPONSE:
How can I help you?
...
```