dev changes

app.py

@@ -1,8 +1,11 @@
 import gradio as gr
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 import torch
+from fastapi import FastAPI
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+app = FastAPI()
+
+model_id = "microsoft/DialoGPT-medium"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -14,12 +17,12 @@ model = AutoModelForCausalLM.from_pretrained(
 generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 
-def chat(message, history=[]): 
-    prompt = f"<s>[INST] {message} [/INST]"
+def chat(message, history=[]):
+    prompt = f"{message}"
     response = generator(prompt, max_new_tokens=256, temperature=0.7)
     reply = response[0]["generated_text"].replace(prompt, "")
     return reply.strip()
 
 
-iface = gr.ChatInterface(fn=chat, title="Mistral Chatbot")
-iface.launch()
+iface = gr.ChatInterface(fn=chat, title="DialoGPT Chatbot")
+app = gr.mount_gradio_app(app, iface, path="/")

requirements.txt

@@ -2,3 +2,5 @@ huggingface_hub==0.25.2
 transformers
 torch
 gradio
+uvicorn
+fastapi