Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Base Model: GPT4-x-Alpaca full fine tune by Chavinlo -> https://huggingface.co/chavinlo/gpt4-x-alpaca
|
| 2 |
+
LORA fine tune using the Roleplay Instruct from GPT4 generated dataset -> https://github.com/teknium1/GPTeacher/tree/main/Roleplay
|
| 3 |
+
|
| 4 |
+
Merged LORA to the model.
|
| 5 |
+
|
| 6 |
+
Instruct it same way as alpaca / gpt4xalpaca:
|
| 7 |
+
```
|
| 8 |
+
### Instruction:
|
| 9 |
+
<prompt>
|
| 10 |
+
### Response:
|
| 11 |
+
|
| 12 |
+
```
|
| 13 |
+
|
| 14 |
+
or
|
| 15 |
+
```
|
| 16 |
+
### Instruction:
|
| 17 |
+
<prompt>
|
| 18 |
+
### Input:
|
| 19 |
+
<specific data to manipulate for the instruction
|
| 20 |
+
### Response:
|
| 21 |
+
|
| 22 |
+
```
|