Update app.py

app.py

@@ -1,18 +1,14 @@
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from llama_cpp import Llama
 import gradio as gr
 
-# Load model and tokenizer
-MODEL_NAME = "vilm/vinallama-2.7b-chat-GGUF"
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+# Load model
+MODEL_PATH = "./model/vinallama-2.7b-chat.gguf"  # Đường dẫn đến mô hình GGUF
+model = Llama(model_path=MODEL_PATH)
 
 # Define chatbot function
 def chatbot(input_text):
-    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
-    outputs = model.generate(inputs["input_ids"], max_length=200, do_sample=True, temperature=0.7)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+    response = model(input_text, max_tokens=200, temperature=0.7)
+    return response['choices'][0]['text']
 
 # Create Gradio interface
 interface = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="Vinamallama 7B Chatbot")