Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- ehartford/samantha-data
|
4 |
+
language:
|
5 |
+
- zh
|
6 |
+
- en
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
---
|
9 |
+
|
10 |
+
# StableBeluga-7B-Qlora-Samantha-Zh-V1
|
11 |
+
|
12 |
+
|
13 |
+
StableBeluga-7B-Qlora-Samantha-Zh-V1 is a conversational AI assistant base on [stabilityai/StableBeluga-7B](https://huggingface.co/stabilityai/StableBeluga-7B) and trained on the samantha-1.1-zh dataset from [ehartford/samantha-data](https://huggingface.co/datasets/ehartford/samantha-data).
|
14 |
+
|
15 |
+
|
16 |
+
## Model Details
|
17 |
+
|
18 |
+
![Train](https://ucarecdn.com/11ea8fe5-322c-41a7-a7cf-36de196f3421/)
|
19 |
+
|
20 |
+
Stable Beluga 7B should be used with this prompt format:
|
21 |
+
|
22 |
+
```
|
23 |
+
### System:
|
24 |
+
This is a system prompt, please behave and help the user.
|
25 |
+
|
26 |
+
### User:
|
27 |
+
Your prompt here
|
28 |
+
|
29 |
+
### Assistant:
|
30 |
+
The output of Stable Beluga 7B
|
31 |
+
```
|