Update README.md

README.md

@@ -147,11 +147,11 @@ def chat():
                 **inputs,
                 max_new_tokens=75,
                 pad_token_id=tokenizer.eos_token_id,
-                temperature=0.3,
-                top_p=0.9,
-                repetition_penalty=1.4,
+                temperature=0.4,
+                top_p=0.85,
+                repetition_penalty=1.3,
                 do_sample=True,
-                no_repeat_ngram_size=2,
+                no_repeat_ngram_size=3,
                 early_stopping=True
             )
 
@@ -177,11 +177,11 @@ chat()
 
 ## Bias, Risks, and Limitations
 
-Not a Substitute for Professional Care - This model is not a licensed mental health professional. Its responses may be incomplete, inaccurate, or unsuitable for serious conditions.
-Inherent Biases - May reflect biases in training data (e.g., cultural assumptions, stigmatizing language).
-Crisis Limitations - Not designed for crisis intervention (e.g., suicidal ideation, self-harm). Always direct users to human professionals or emergency services.
-Over-Reliance Risk - Outputs could inadvertently worsen symptoms if users interpret them as definitive advice.
-*Intended Use - Assist with general emotional support, not diagnosis or treatment.
+* Not a Substitute for Professional Care: This model is not a licensed mental health professional. Its responses may be incomplete, inaccurate, or unsuitable for serious conditions.
+* Inherent Biases - May reflect biases in training data (e.g., cultural assumptions, stigmatizing language).
+* Crisis Limitations - Not designed for crisis intervention (e.g., suicidal ideation, self-harm). Always direct users to human professionals or emergency services.
+* Over-Reliance Risk - Outputs could inadvertently worsen symptoms if users interpret them as definitive advice.
+* Intended Use - Assist with general emotional support, not diagnosis or treatment.
 
 ### Model Sources [optional]