Update README.md

README.md

@@ -9,7 +9,8 @@ tags:
 
 # Limamono-7B (Mistral) v0.3
 This is a very early version of a strongly NSFW roleplaying model with _extremely limited amounts_
-of almost entirely synthetic data of hopefully higher quality than typical human conversations.
+of almost entirely synthetic data of hopefully higher quality than typical human conversations. The
+intended model audience is straight men and lesbians.
 
 Limamono tries to address the main issues and limitations of the previously released [LimaRP](https://huggingface.co/datasets/lemonilia/LimaRP)
 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
 
 **Note**: there is currently no plan to release the dataset.
 
+## Known issues and quirks
+- The model may feel somewhat "overbaked".
+- Impersonation may still sometimes occur early in the chat, in particular when trying to force a long
+  character message length.
+
 ## Prompt format
 Limamono uses the [extended Alpaca format](https://github.com/tatsu-lab/stanford_alpaca),
 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:
 This has an effect on bot responses, but as of now it might not always reliably work. The lengths
 using during training are: `micro`, `tiny`, `short`, `medium`, `long`, `massive`, `huge`.
 
-- It is recommended not to use a length modifier at all for character responses, except as a
-  _temporary measure_ for increasing message length.
-- It is suggested to add `(length = tiny)` to the `### Input:` sequence, on the other hand.
+However, it is recommended **not** to use a length modifier at all for character responses, except as a
+_temporary measure_ for increasing message length in case they become too short.
+
+On the other hand, it is suggested to add `(length = tiny)` or `(length = short)` to the
+`### Input:` sequence, in order to help the model follow more closely its training data.
 
 ## Prose style
 Only The Novel/Forum RP style is supported.
@@ -89,12 +97,21 @@ Only The Novel/Forum RP style is supported.
   - `''The Jungle Book''`
 - Punctuation has been normalized and tries to follow standard convensions for book/novel writing.
 
+## SillyTavern settings
+Try to follow these settings. Appropriate files for replicating them are included in the model
+repository:
+
+![ST settings](https://files.catbox.moe/z9q0g2.png)
+
 ## Example
 This is how a typical RP chat may take place with this model. Note the presence of
 character thoughts.
 
 ![example](https://files.catbox.moe/ch2bo2.png)
 
+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)
+in the repository.
+
 ## Training procedure
 [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
 on one NVidia RTX3090.