Update app.py

app.py

@@ -110,8 +110,8 @@ def chat_inf_a(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p
     if len(client_choice)>=hid_val:
         if system_prompt:
             system_prompt=f'{system_prompt}, '
-        #client1=client_z[int(hid_val)-1]
-        client1=gr.load("models/" + models[0])
+        client1=client_z[int(hid_val)-1]
+        #client1=gr.load("models/" + models[0])
         if not history:
             history = []
             hist_len=0
@@ -125,7 +125,7 @@ def chat_inf_a(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p
         )
         #formatted_prompt=prompt   
         formatted_prompt = format_prompt_choose(f"{system_prompt}{prompt}", history, client_choice[0])
-        stream1 = client1.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+        stream1 = client1(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
         output = ""
         for response in stream1:
             output += response.token.text
@@ -155,7 +155,7 @@ def chat_inf_b(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p
         )
         #formatted_prompt=prompt   
         formatted_prompt = format_prompt_choose(f"{system_prompt}{prompt}", history, client_choice[1])
-        stream2 = client2.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+        stream2 = client2(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
         output = ""
         for response in stream2:
             output += response.token.text
@@ -184,7 +184,7 @@ def chat_inf_c(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p
         )
         #formatted_prompt=prompt   
         formatted_prompt = format_prompt_choose(f"{system_prompt}{prompt}", history, client_choice[2])
-        stream3 = client3.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+        stream3 = client3(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
         output = ""
         for response in stream3:
             output += response.token.text
@@ -213,7 +213,7 @@ def chat_inf_d(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p
         )
         #formatted_prompt=prompt   
         formatted_prompt = format_prompt_choose(f"{system_prompt}{prompt}", history, client_choice[3])
-        stream4 = client4.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+        stream4 = client4(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
         output = ""
         for response in stream4:
             output += response.token.text