updated app.py

app.py

@@ -1,3 +1,43 @@
+from transformers import pipeline
+import gradio as gr
+
+chatbot = pipeline(model="ivwhy/lora_model")
+
+message_list = []
+response_list = []
+
+def chat_function(message, history, system_prompt, max_new_tokens, temperature):
+    messages = [{"role":"system","content":system_prompt},
+                {"role":"user","content":message}]
+    prompt = pipeline.tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,)
+    terminators = [
+        pipeline.tokenizer.eos_token_id,
+        pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")]
+    outputs = pipeline(
+        prompt,
+        max_new_tokens = max_new_tokens,
+        eos_token_id = terminators,
+        do_sample = True,
+        temperature = 0.1,
+        top_p = 0.9,)
+    return outputs[0]["generated_text"][len(prompt):]
+
+demo_chatbot = gr.ChatInterface(
+    chat_function,
+    textbox=gr.Textbox(placeholder="Enter message here", container=False, scale=7),
+    chatbot=gr.Chatbot(height=400),
+    additional_inputs=[
+        gr.Textbox("You are helpful AI", label="System Prompt"),
+        gr.Slider(500,4000, label="Max New Tokens"),
+        gr.Slider(0,1,label="Temperature")
+    ])
+
+demo_chatbot.launch()
+
+''' =================================== OLD VERSION ==============================================
 import torch
 import transformers
 import gradio as gr
@@ -78,7 +118,7 @@ demo = gr.ChatInterface(
 if __name__ == "__main__":
     demo.launch()
 
-'''================================== OLD VER ==============================
+================================== OLD VER ==============================
 import torch
 import transformers
 import gradio as gr