Lewdiculous
commited on
Commit
•
b403657
1
Parent(s):
45c87f3
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,64 @@
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
license: apache-2.0
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- gguf
|
8 |
+
- quantized
|
9 |
+
- roleplay
|
10 |
+
- imatrix
|
11 |
+
- mistral
|
12 |
+
- merge
|
13 |
+
inference: false
|
14 |
+
base_model:
|
15 |
+
- ResplendentAI/Datura_7B
|
16 |
+
- ChaoticNeutrals/Eris_Floramix_DPO_7B
|
17 |
---
|
18 |
+
|
19 |
+
This repository hosts GGUF-Imatrix quantizations for [Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B).
|
20 |
+
```
|
21 |
+
Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
|
22 |
+
```
|
23 |
+
To be uploaded:
|
24 |
+
```python
|
25 |
+
quantization_options = [
|
26 |
+
"Q4_K_M", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
|
27 |
+
"Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
|
28 |
+
]
|
29 |
+
```
|
30 |
+
|
31 |
+
**This is experimental.**
|
32 |
+
|
33 |
+
For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt).
|
34 |
+
|
35 |
+
**Original model information:**
|
36 |
+
|
37 |
+
This is an experimental model I currently use. It's far from great as I'm still working on it, but I leave it here for people to try if interested in this format.
|
38 |
+
This model was basically made to stop some upsetting hallucinations, so {{char}} mostly and occasionally will wait {{user}} response instead of responding itself or deciding for {{user}}, also, my primary idea was to create a cozy model that thinks.*
|
39 |
+
|
40 |
+
Inspired by [lemonilia/Limamono-Mistral-7B-v0.50](https://huggingface.co/lemonilia/Limamono-Mistral-7B-v0.50)
|
41 |
+
### Style details:
|
42 |
+
- Quotes are used for character dialogs.
|
43 |
+
- `"Hey, Anon... What do you think about my style?"`
|
44 |
+
- Asterisks can be used for narration, but it's optional, it's recommended to use default novel format.
|
45 |
+
- `*Her cheeks blush slightly, she tries to hide.*`
|
46 |
+
- Character thoughts are wrapped with ` marks. **This may often spontaneously occur.**
|
47 |
+
- `My heart skips a beat hearing him call me pretty!`
|
48 |
+
|
49 |
+
*If you want thoughts to appear more often, just add something like this to your system prompt: ```"{{char}} internal thoughts are wrapped with ` marks."```*
|
50 |
+
|
51 |
+
- Accepted response lengths: ***tiny, short, medium, long, huge***
|
52 |
+
-
|
53 |
+
For example: ### Response: (length = medium)
|
54 |
+
|
55 |
+
Note: Apparently ***humongous***, ***extreme*** and ***unlimited*** may not work at moment. Not fully tested.
|
56 |
+
|
57 |
+
### Prompt format:
|
58 |
+
Extended Alpaca, as always.
|
59 |
+
|
60 |
+
``"You are now in roleplay chat mode. Engage in an endless chat with {{user}}. Always wait {{user}} turn, next actions and responses."``
|
61 |
+
|
62 |
+
## Example:
|
63 |
+
|
64 |
+
![example](https://files.catbox.moe/j0zxov.png)
|