Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import plotly.express as px
 import os
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, BlenderbotForConditionalGeneration
 
 # Check if CUDA is available and set device accordingly
 device = "cuda" if torch.cuda.is_available() else "cpu"
@@ -25,14 +25,23 @@ def hermes_model():
 
 
 def blender_model():
+    model = BlenderbotForConditionalGeneration.from_pretrained("facebook/blenderbot-400M-distill")
     tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")
-    model = AutoModelForCausalLM.from_pretrained("facebook/blenderbot-400M-distill", low_cpu_mem_usage=True, device_map="auto")
     return model, tokenizer
 
 model, tokenizer = blender_model()
 
-# Function to generate a response from the model
 def chat_response(msg_prompt: str) -> str:
+    inputs = tokenizer([UTTERANCE], return_tensors="pt")
+    reply_ids = model.generate(**inputs)
+    outputs = tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0])
+  
+        return outputs
+    except Exception as e:
+        return str(e)
+
+# Function to generate a response from the model
+def chat_responses(msg_prompt: str) -> str:
     """
     Generates a response from the model given a prompt.