practicaldreamer commited on
Commit
2166fb5
1 Parent(s): a9e2886

formatting

Browse files
Files changed (1) hide show
  1. README.md +11 -10
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
- Duration: ~4hrs
19
- GPU: 1xA100 80GB
20
- Epochs: 1.08
21
- Speed: 3e-5
22
- Sequence_len: 2048
 
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
- ## Expected Prompt Format
33
- **Context/Memory**
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
- **Turn Template**
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 (User is Baloo from The Jungle Book. Bot is Queen of Hearts from Alice in Wonderland)
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