fix </s> v2

app.py

@@ -10,19 +10,21 @@ def generate_response(chat, kwargs):
     stream = client.text_generation(chat, **kwargs, stream=True, details=True, return_full_text=False)
     for response in stream:
         output += response.token.text
+    if output.endswith("</s>"):  # Sprawdzamy, czy odpowiedź kończy się tagiem </s>
+        output = output[:-4]  # Usuwamy tag </s> z końca odpowiedzi
     return output
 
-def function(prompt, history=[]):  # Tutaj dodajemy history jako opcjonalny parametr
+def function(prompt, history=[]):
     chat = "<s>"
     for user_prompt, bot_response in history:
         chat += f"[INST] {user_prompt} [/INST] {bot_response}</s> <s>"
-    chat += f"[INST] {prompt} [/INST]"
+    chat += f"[INST] {prompt} [/INST]"  # Zostawiamy tylko tag otwierający <s> na początku i kończymy ciąg zwykłym znacznikiem
     kwargs = dict(
-        temperature=0.80,
-        max_new_tokens=2048,
+        temperature=0.5,
+        max_new_tokens=4096,
         top_p=0.95,
         repetition_penalty=1.0,
-        do_sample=True,  # Upewnij się, że używasz próbkowania
+        do_sample=True,
         seed=1337
     )
 
@@ -53,5 +55,4 @@ interface = gr.ChatInterface(
     clear_btn=None
 )
 
-# Ustawienie share=True pozwala na stworzenie publicznego linku do aplikacji
 interface.launch(show_api=True, share=True)