KnutJaegersberg
commited on
Commit
•
7e2921d
1
Parent(s):
38cfb67
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,27 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
+
datasets:
|
4 |
+
- KnutJaegersberg/facehugger
|
5 |
---
|
6 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/4OQkvAa1zOK4Devv-aUdL.png)
|
7 |
+
|
8 |
+
|
9 |
+
This model was fine tuned on AI filtered subsets of GPT-4 based subset of the Dolphin dataset and EvolInstruct V2.
|
10 |
+
It has not been explicitly aligned to positive, negative or bureaucratically prescribed value systems.
|
11 |
+
It might kill us all! Time to shit your pants, regulators. I literally put black goo on Dolphin-7B sperm, which then fertilized Evolved Instructions...
|
12 |
+
What's different is evil... ;)
|
13 |
+
I intend to train 3 sizes.
|
14 |
+
|
15 |
+
Prompt Example:
|
16 |
+
```
|
17 |
+
### System:
|
18 |
+
|
19 |
+
You are an AI assistant. User will you give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
|
20 |
+
|
21 |
+
|
22 |
+
### Instruction:
|
23 |
+
|
24 |
+
How do you fine tune a large language model?
|
25 |
+
|
26 |
+
### Response:
|
27 |
+
```
|