Update app.py

app.py

@@ -168,65 +168,8 @@
 
 
 
-# from huggingface_hub import InferenceClient
-# import gradio as gr  
-# client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
-
-# def format_prompt(message, history):
-#   prompt = "<s>"
-#   for user_prompt, bot_response in history:
-#     prompt += f"[INST] {user_prompt} [/INST]"
-#     prompt += f" {bot_response}</s> "
-#   prompt += f"[INST] {message} [/INST]"
-#   return prompt
-
-# def generate(
-#     prompt, history, temperature=0.2, max_new_tokens=3000, top_p=0.95, repetition_penalty=1.0,
-# ):
-#     temperature = float(temperature)
-#     if temperature < 1e-2:
-#         temperature = 1e-2
-#     top_p = float(top_p)
-
-#     generate_kwargs = dict(
-#         temperature=temperature,
-#         max_new_tokens=max_new_tokens,
-#         top_p=top_p,
-#         repetition_penalty=repetition_penalty,
-#         do_sample=True,
-#         seed=42,
-#     )
-
-#     formatted_prompt = format_prompt(prompt, history)
-
-#     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-#     output = ""
-
-#     for response in stream:
-#         output += response.token.text
-#         yield output
-#     return output
-
-    
-# mychatbot = gr.Chatbot(
-#     avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
-
-# demo = gr.ChatInterface(fn=generate, 
-#                         chatbot=mychatbot,
-#                         title="Mistral-Chat",
-#                         retry_btn=None,
-#                         undo_btn=None
-#                        )
-
-# demo.queue().launch(show_api=False)
-
-
-
-
-
 from huggingface_hub import InferenceClient
-import gradio as gr
-
+import gradio as gr  
 client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
 
 def format_prompt(message, history):
@@ -238,7 +181,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, history, temperature=0.3, max_new_tokens=3000, top_p=0.90
+    prompt, history, temperature=0.3, max_new_tokens=3000, top_p=0.90, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -249,9 +192,9 @@ def generate(
         temperature=temperature,
         max_new_tokens=max_new_tokens,
         top_p=top_p,
-        #repetition_penalty=repetition_penalty,
-        #do_sample=True,
-        #seed=42,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
     )
 
     formatted_prompt = format_prompt(prompt, history)
@@ -263,8 +206,7 @@ def generate(
         output += response.token.text
         yield output
     return output
-
-
+    
 additional_inputs=[
     gr.Slider(
         label="temperature",
@@ -296,13 +238,16 @@ additional_inputs=[
     )
 ]
 
-bbchatbot = gr.Chatbot(
+    
+mychatbot = gr.Chatbot(
     avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
 
 demo = gr.ChatInterface(fn=generate, 
-                        chatbot=bbchatbot,
+                        chatbot=mychatbot,
                         title="Mistral-Chat",
-                        additional_inputs=additional_inputs
+                        additional_inputs=additional_inputs,
+                        retry_btn=None,
+                        undo_btn=None
                        )
 
 demo.queue().launch(show_api=False)
@@ -312,4 +257,3 @@ demo.queue().launch(show_api=False)
 
 
 
-