Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- PygmalionAI/PIPPA
|
4 |
+
- lemonilia/LimaRP
|
5 |
+
---
|
6 |
+
|
7 |
+
big thanks to lore for the 8xH100 gpus
|
8 |
+
|
9 |
+
## awq
|
10 |
+
|
11 |
+
zero point, 128 group size, 4 bit gemm
|
12 |
+
|
13 |
+
## training
|
14 |
+
|
15 |
+
base model is meta llama 3 8b instruct
|
16 |
+
trained on pippa then i trained that model on limarp, both at 8k context
|
17 |
+
|
18 |
+
## gen settings
|
19 |
+
|
20 |
+
i would **start with** every sampler off and **temperature at 1 and just make min p 0.05**, i got good prompts from this but u can also try to gen settings from shori which are copy pasted below
|
21 |
+
|
22 |
+
- **Main choice** (may have repetition issues)
|
23 |
+
- **Temperature**: 1.0; **Min-P**: 0.05-0.10; **Presence Penalty**: 0.35-0.45
|
24 |
+
- **Alternative 1** (appears to solve repetition issues while being coherent, but reponses might possibly be less truthful)
|
25 |
+
- **Temperature**: 2.40-2.50; **Min-P**: 0.40; **Frequency penalty**: 0.10-0.15; Temperature last.
|
26 |
+
- **Alternative 2**
|
27 |
+
- **Mirostat type**: 2, **Mirostat Tau**: 2.80-3.00; **Mirostat Eta**: 0.0175-0.0200; neutralize or disable all other samplers
|
28 |
+
|
29 |
+
## prompting
|
30 |
+
|
31 |
+
use the llama 3 instruct format
|
32 |
+
|
33 |
+
ST jsons:
|
34 |
+
[instruct](https://files.catbox.moe/ocnjb7.json)
|
35 |
+
[context](https://files.catbox.moe/hjkawf.json)
|
36 |
+
|
37 |
+
agnaistic prompt:
|
38 |
+
```
|
39 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{#if system}}<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{system}}<|eot_id|>{{/if}}Write {{char}}'s next reply in a fictional roleplay chat between {{#each bot}}{{.name}}, {{/each}}{{char}} and {{user}}.
|
40 |
+
|
41 |
+
{{char}}'s Persona: {{personality}}
|
42 |
+
|
43 |
+
{{#if memory}}
|
44 |
+
Important details:
|
45 |
+
{{memory}}
|
46 |
+
{{/if}}
|
47 |
+
|
48 |
+
{{#if example_dialogue}}This is how {{char}} should talk:
|
49 |
+
{{example_dialogue}}{{/if}}
|
50 |
+
|
51 |
+
This scenario of the conversation: {{scenario}}
|
52 |
+
|
53 |
+
Then the roleplay chat between {{#each bot}}{{.name}}, {{/each}}{{char}} and {{user}} begins.<|eot_id|>
|
54 |
+
|
55 |
+
{{#each msg}}{{#if .isbot}}<|start_header_id|>response<|end_header_id|>{{/if}}{{#if .isuser}}<|start_header_id|>user<|end_header_id|>{{/if}}{{.name}}: {{.msg}}<|eot_id|>
|
56 |
+
{{/each}}
|
57 |
+
{{#if ujb}}<|begin_of_text|><|start_header_id|>system<|end_header_id|>{{ujb}}<|eot_id|>{{/if}}
|
58 |
+
<|start_header_id|>response<|end_header_id|>{{post}}
|
59 |
+
```
|