practicaldreamer
commited on
Commit
·
2166fb5
1
Parent(s):
a9e2886
formatting
Browse files
README.md
CHANGED
@@ -15,22 +15,23 @@ Intended for research, creative writing, entertainment, DnD campaigns? fun!
|
|
15 |
|
16 |
## Train Summary
|
17 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
|
|
23 |
gradient_accumulation_steps: 32
|
24 |
wandb link: https://wandb.ai/practicaldreamer/rpgpt/runs/d4gsi8vy
|
25 |
-
|
26 |
*Please see the documentation folder for more information*
|
27 |
|
28 |
## Usage
|
29 |
This LoRA was trained for use with **Neko-Institute-of-Science/LLaMA-30B-HF**
|
30 |
Follow the expected Prompt Format.
|
31 |
|
32 |
-
##
|
33 |
-
|
34 |
```
|
35 |
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
36 |
|
@@ -47,7 +48,7 @@ USER: Write a character roleplay dialogue using asterisk roleplay format based o
|
|
47 |
|
48 |
ASSISTANT:
|
49 |
```
|
50 |
-
|
51 |
```
|
52 |
<User-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
|
53 |
<Bot-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
|
@@ -56,7 +57,7 @@ ASSISTANT:
|
|
56 |
...
|
57 |
```
|
58 |
|
59 |
-
## Example
|
60 |
```
|
61 |
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
62 |
|
|
|
15 |
|
16 |
## Train Summary
|
17 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
18 |
+
```
|
19 |
+
duration: ~4hrs
|
20 |
+
gpu: 1xA100 80GB
|
21 |
+
epochs: 1.08
|
22 |
+
speed: 3e-5
|
23 |
+
sequence_len: 2048
|
24 |
gradient_accumulation_steps: 32
|
25 |
wandb link: https://wandb.ai/practicaldreamer/rpgpt/runs/d4gsi8vy
|
26 |
+
```
|
27 |
*Please see the documentation folder for more information*
|
28 |
|
29 |
## Usage
|
30 |
This LoRA was trained for use with **Neko-Institute-of-Science/LLaMA-30B-HF**
|
31 |
Follow the expected Prompt Format.
|
32 |
|
33 |
+
## Prompt Format
|
34 |
+
Context/Memory:
|
35 |
```
|
36 |
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
37 |
|
|
|
48 |
|
49 |
ASSISTANT:
|
50 |
```
|
51 |
+
Turn Template:
|
52 |
```
|
53 |
<User-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
|
54 |
<Bot-Character Name>: \*<1st person action/sensations/thoughts>\* <Spoken Word> \*<1st person action/sensations/thoughts>\*
|
|
|
57 |
...
|
58 |
```
|
59 |
|
60 |
+
## Example
|
61 |
```
|
62 |
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
|
63 |
|