Update README.md

README.md

@@ -6,9 +6,9 @@ language:
 
 # Talosian-7B
 
-Talosian-7B is an erotic storytelling model built for the specific purpose of controllably writing new stories section-by-section.
+Talosian-7B is a storytelling model built for the specific purpose of controllably writing new stories section-by-section.
 
-It is trained from the new Mistral-7B v0.2 base model on a long-context dataset of smut stories.
+It is trained from the new Mistral-7B v0.2 base model on a long-context dataset of smut stories. It can generalize to a variety of types of romance or erotic stories, but its voice is by default similar to traditional smut writing.
 
 ## Prompt Format
 
@@ -134,4 +134,12 @@ Finally, Juliet spoke up. “Maybe we could run a layer interleaving model merge
 ...
 </details>
 
-Talosian is _not_ a user <-> assistant chat-formatted model. All prompting should be done as completions (for example, in text-generation-webui's Notebook mode.)
+Talosian is _not_ a user <-> assistant chat-formatted model. All prompting should be done as completions (for example, in text-generation-webui's Notebook mode.)
+
+## Generation Parameters
+
+Text-generation-webui's default parameters work well. Temperature should be between 0.5 and 0.9. Consider adding `[SEC]` as a custom stopping string if you'd like to only generate one section at a time.
+
+## Model Details
+
+Talosian shares Mistral 7B v0.2's context length of 32k tokens. Ensure that `rope_frequency_base`/`rope_theta` is set to `1000000` when loading the model.