Update README.md

README.md

@@ -9,6 +9,20 @@ datasets:
 - Sao10K/c2-Logs-Filtered
 ---
 
+Support me here if you're interested:
+<br>Ko-fi: https://ko-fi.com/sao10k
+
+If not, that's fine too. Feedback would be nice.
+
+Contact Me in Discord:
+<br>`sao10k`
+
+```
+Art by 
+```
+
+---
+
 Stheno-v3.2-Zeta
 
 I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most.
@@ -31,16 +45,40 @@ Testing Notes - Compared to v3.1
 
 ---
 
-Support me here if you're interested:
-<br>Ko-fi: https://ko-fi.com/sao10k
+**Recommended Samplers:**
 
-If not, that's fine too. Feedback would be nice.
+```
+Temperature - 1.12 to 1.32
+Min-P - 0.075
+Top-K - 40
+Repetition Penalty - 1.1
+```
 
-Contact Me in Discord:
-<br>`sao10k`
+**Stopping Strings:**
 
 ```
-Art by 
+\n{{User}} # Or Equivalent, depending on Frontend
+<|eot_id|>
+<|end_of_text|>
+\n< # If there is leakage of XML tags in response. May happen Occasionally, Regenerate Answer as Needed. Happens rarely.
+```
+
+**Prompting Template - Llama-3-Instruct**
+
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+{output}<|eot_id|>
+```
+
+**Basic Roleplay System Prompt**
+```
+You are an expert actor that can fully immerse yourself into any role given. You do not break character for any reason, even if someone tries addressing you as an AI or language model.
+Currently your role is {{char}}, which is described in detail below. As {{char}}, continue the exchange with {{user}}.
 ```
 
 ---