Update run.py

run.py

@@ -246,19 +246,19 @@ def response(message, history,customSysPrompt,settings):
   
   print("AI running on prem!" if(onPrem) else "AI running HFHub!")
   if(onPrem==False):
-    temperature=float(0.9) 
-    max_new_tokens=500 
-    top_p=0.95 
-    repetition_penalty=1.0
-    if temperature < 1e-2: temperature = 1e-2
-    top_p = float(top_p)
-    generate_kwargs = dict(
+    generate_kwargs = dict( #https://github.com/huggingface/chat-ui/blob/main/.env.template
+        temperature=0.6,
+        top_p=0.95,
+        repetition_penalty=1.2,
+        top_k=50,
+        truncate=24576,
+        max_new_tokens=8192
         #temperature=temperature,
-        max_new_tokens=max_new_tokens,
+        #max_new_tokens=max_new_tokens,
         #top_p=top_p,
         #repetition_penalty=repetition_penalty,
         #do_sample=True,
-        seed=42,
+        #seed=42,
     )
     stream = client.text_generation(prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     response = ""