digitalpipelines
commited on
Commit
•
dc22a4d
1
Parent(s):
ffc11ee
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
license: apache-2.0
|
2 |
+
datasets:
|
3 |
+
- wikitext
|
4 |
+
tags:
|
5 |
+
- digitalpipelines
|
6 |
+
---
|
7 |
+
|
8 |
+
# Overview
|
9 |
+
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)
|
10 |
+
|
11 |
+
# Prompt style
|
12 |
+
The model was trained with the following prompt style:
|
13 |
+
```
|
14 |
+
### HUMAN:
|
15 |
+
Hello
|
16 |
+
|
17 |
+
### RESPONSE:
|
18 |
+
Hi, how are you?
|
19 |
+
|
20 |
+
### HUMAN:
|
21 |
+
I'm fine.
|
22 |
+
|
23 |
+
### RESPONSE:
|
24 |
+
How can I help you?
|
25 |
+
...
|
26 |
+
```
|