File size: 889 Bytes
122861e 7058ea1 d384792 a21ed5c 7058ea1 d384792 7058ea1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 |
---
tags:
- mistral
- merge
---
## A merge of the following models using a custom NearSwap algorithm:
* [fearlessdots/WizardLM-2-7B-abliterated](https://huggingface.co./fearlessdots/WizardLM-2-7B-abliterated)
* [Virt-io/Erebus-Holodeck-7B](https://huggingface.co./Virt-io/Erebus-Holodeck-7B)
With [fearlessdots/WizardLM-2-7B-abliterated](https://huggingface.co./fearlessdots/WizardLM-2-7B-abliterated) as the base model.
<b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> and supports **multi-turn** conversation. The prompt should be as following:
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: Who are you? ASSISTANT: I am WizardLM.</s>......
```
<b>Add Genre's in a list like this.</b>
```
[Genre: <genre1>, <genre2>]
``` |