Update app.py

app.py

@@ -13,17 +13,17 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 
-#chatbot = pipeline(model="NCSOFT/Llama-3-OffsetBias-8B")
+chatbot = pipeline(model="microsoft/Phi-3.5-mini-instruct")
 #token = os.getenv("HF_TOKEN")
-login(token = os.getenv('HF_TOKEN'))
+#login(token = os.getenv('HF_TOKEN'))
 #chatbot = pipeline(model="meta-llama/Llama-3.2-1B")
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
-model = AutoModelForCausalLM.from_pretrained(
-    "meta-llama/Llama-3.2-1B-Instruct",
-    device_map="auto",
-    torch_dtype="auto",
-)
+#tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
+#model = AutoModelForCausalLM.from_pretrained(
+#    "meta-llama/Llama-3.2-1B-Instruct",
+#    device_map="auto",
+#    torch_dtype="auto",
+#)
 
 #chatbot = pipeline(model="facebook/blenderbot-400M-distill")
 
@@ -32,13 +32,13 @@ response_list = []
 
 
 def vanilla_chatbot(message, history):
-    inputs = tokenizer(message, return_tensors="pt").to("cpu")
-    with torch.no_grad():
-        outputs = model.generate(inputs.input_ids, max_length=100)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
-    #conversation = chatbot(message)
+    #inputs = tokenizer(message, return_tensors="pt").to("cpu")
+    #with torch.no_grad():
+    #    outputs = model.generate(inputs.input_ids, max_length=100)
+    #return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    conversation = chatbot(message)
     
-    #return conversation[0]['generated_text']
+    return conversation[0]['generated_text']
 
 demo_chatbot = gr.ChatInterface(vanilla_chatbot, title="Vanilla Chatbot", description="Enter text to start chatting.")