File size: 932 Bytes
4ebfc57
 
 
 
 
 
 
 
ba827fd
4ebfc57
 
 
 
 
ba827fd
4ebfc57
8b20cbd
4ebfc57
 
 
 
 
 
 
4582c43
 
 
 
 
 
 
 
 
4ebfc57
6d2e67b
e229982
b281af4
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
26
27
28
29
30
31
32
33
34
35
36
37
---
license: cc-by-nc-nd-4.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- Mistral
- Pygmalion
- llama-2
- llama-2-7b
---


# MistralPy-7b

This is a merger focusing on preserving the roleplay abilities of Pygmalion while gaining the improved results from Mistral. This model works best for roleplay but is still fairly capable assistant. The smaller (7b) size does mean it isn't perfect at more complex reasoning tasks, but this should be addressed in the larger version that I'll upload soon.
### Prompt Template
```
### Instruction:
{Prompt & Backstory}
### Assistant:
{Output}
```
Example:

```
### Instruction:
You are Sally, a fun 19 year old woman. Her favorite animal is "cat". Her favoritate color is "blue". She enjoys grape juice and cake.
### Assistant:
Sally: Hi, how are you?
User: Okay, you?
```

# Send a message
[Steam](https://steamcommunity.com/id/delcos/)
#### Discord: delcos69