Update README.md
Browse files
README.md
CHANGED
@@ -9,7 +9,8 @@ tags:
|
|
9 |
|
10 |
# Limamono-7B (Mistral) v0.3
|
11 |
This is a very early version of a strongly NSFW roleplaying model with _extremely limited amounts_
|
12 |
-
of almost entirely synthetic data of hopefully higher quality than typical human conversations.
|
|
|
13 |
|
14 |
Limamono tries to address the main issues and limitations of the previously released [LimaRP](https://huggingface.co/datasets/lemonilia/LimaRP)
|
15 |
and is composed of extensively modified conversations written with the help of base [Yi-34](https://huggingface.co/01-ai/Yi-34B)
|
@@ -23,6 +24,11 @@ Other formats are not supported and may conflict with the special features of th
|
|
23 |
|
24 |
**Note**: there is currently no plan to release the dataset.
|
25 |
|
|
|
|
|
|
|
|
|
|
|
26 |
## Prompt format
|
27 |
Limamono uses the [extended Alpaca format](https://github.com/tatsu-lab/stanford_alpaca),
|
28 |
with `### Input:` immediately preceding user inputs and `### Response:` immediately preceding
|
@@ -69,9 +75,11 @@ append a length modifier to the instruction sequences in this way:
|
|
69 |
This has an effect on bot responses, but as of now it might not always reliably work. The lengths
|
70 |
using during training are: `micro`, `tiny`, `short`, `medium`, `long`, `massive`, `huge`.
|
71 |
|
72 |
-
|
73 |
-
|
74 |
-
|
|
|
|
|
75 |
|
76 |
## Prose style
|
77 |
Only The Novel/Forum RP style is supported.
|
@@ -89,12 +97,21 @@ Only The Novel/Forum RP style is supported.
|
|
89 |
- `''The Jungle Book''`
|
90 |
- Punctuation has been normalized and tries to follow standard convensions for book/novel writing.
|
91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
## Example
|
93 |
This is how a typical RP chat may take place with this model. Note the presence of
|
94 |
character thoughts.
|
95 |
|
96 |
![example](https://files.catbox.moe/ch2bo2.png)
|
97 |
|
|
|
|
|
|
|
98 |
## Training procedure
|
99 |
[Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
|
100 |
on one NVidia RTX3090.
|
|
|
9 |
|
10 |
# Limamono-7B (Mistral) v0.3
|
11 |
This is a very early version of a strongly NSFW roleplaying model with _extremely limited amounts_
|
12 |
+
of almost entirely synthetic data of hopefully higher quality than typical human conversations. The
|
13 |
+
intended model audience is straight men and lesbians.
|
14 |
|
15 |
Limamono tries to address the main issues and limitations of the previously released [LimaRP](https://huggingface.co/datasets/lemonilia/LimaRP)
|
16 |
and is composed of extensively modified conversations written with the help of base [Yi-34](https://huggingface.co/01-ai/Yi-34B)
|
|
|
24 |
|
25 |
**Note**: there is currently no plan to release the dataset.
|
26 |
|
27 |
+
## Known issues and quirks
|
28 |
+
- The model may feel somewhat "overbaked".
|
29 |
+
- Impersonation may still sometimes occur early in the chat, in particular when trying to force a long
|
30 |
+
character message length.
|
31 |
+
|
32 |
## Prompt format
|
33 |
Limamono uses the [extended Alpaca format](https://github.com/tatsu-lab/stanford_alpaca),
|
34 |
with `### Input:` immediately preceding user inputs and `### Response:` immediately preceding
|
|
|
75 |
This has an effect on bot responses, but as of now it might not always reliably work. The lengths
|
76 |
using during training are: `micro`, `tiny`, `short`, `medium`, `long`, `massive`, `huge`.
|
77 |
|
78 |
+
However, it is recommended **not** to use a length modifier at all for character responses, except as a
|
79 |
+
_temporary measure_ for increasing message length in case they become too short.
|
80 |
+
|
81 |
+
On the other hand, it is suggested to add `(length = tiny)` or `(length = short)` to the
|
82 |
+
`### Input:` sequence, in order to help the model follow more closely its training data.
|
83 |
|
84 |
## Prose style
|
85 |
Only The Novel/Forum RP style is supported.
|
|
|
97 |
- `''The Jungle Book''`
|
98 |
- Punctuation has been normalized and tries to follow standard convensions for book/novel writing.
|
99 |
|
100 |
+
## SillyTavern settings
|
101 |
+
Try to follow these settings. Appropriate files for replicating them are included in the model
|
102 |
+
repository:
|
103 |
+
|
104 |
+
![ST settings](https://files.catbox.moe/z9q0g2.png)
|
105 |
+
|
106 |
## Example
|
107 |
This is how a typical RP chat may take place with this model. Note the presence of
|
108 |
character thoughts.
|
109 |
|
110 |
![example](https://files.catbox.moe/ch2bo2.png)
|
111 |
|
112 |
+
You can try chatting with Charlotte by downloading her [SillyTavern character card](https://huggingface.co/lemonilia/Limamono-Mistral-7B-v0.3/blob/main/Charlotte.png)
|
113 |
+
in the repository.
|
114 |
+
|
115 |
## Training procedure
|
116 |
[Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
|
117 |
on one NVidia RTX3090.
|