PEFT
Not-For-All-Audiences
kingbri commited on
Commit
f30968e
1 Parent(s): 7aa2af3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -25,6 +25,16 @@ You can read more about the dataset on its relevant page. It's a ShareGPT reform
25
  - **Training Environment**: Axolotl
26
  - **sequence_len**: 4096
27
 
 
 
 
 
 
 
 
 
 
 
28
  ## Notes
29
 
30
  This Qlora was produced as an experiment to see how the public version of PIPPA can affect a model. As a result, I have no idea if this lora is of great quality or absolute garbage.
@@ -35,6 +45,11 @@ Thanks to:
35
  - PygmalionAI: The creators of the PIPPA dataset
36
  - Axolotl: Finetuning suite
37
 
 
 
 
 
 
38
  ## Axolotl stuff
39
 
40
  ## Training procedure
 
25
  - **Training Environment**: Axolotl
26
  - **sequence_len**: 4096
27
 
28
+ ## Instruct Format
29
+
30
+ ShareGPT gets converted to vicuna format. The dataset uses modified roles of `USER` and `CHARACTER` instead of `USER` and `ASSISTANT`.
31
+
32
+ ```
33
+ SYSTEM: Enter roleplay mode...
34
+ USER: {prompt}
35
+ CHARACTER:
36
+ ```
37
+
38
  ## Notes
39
 
40
  This Qlora was produced as an experiment to see how the public version of PIPPA can affect a model. As a result, I have no idea if this lora is of great quality or absolute garbage.
 
45
  - PygmalionAI: The creators of the PIPPA dataset
46
  - Axolotl: Finetuning suite
47
 
48
+ ## Donate?
49
+ All my infrastructure and cloud expenses are paid out of pocket. If you'd like to donate, you can do so here: [https://ko-fi.com/kingbri](https://ko-fi.com/kingbri)
50
+
51
+ You should not feel obligated to donate, but if you do, I'd appreciate it.
52
+
53
  ## Axolotl stuff
54
 
55
  ## Training procedure