Update app.py

app.py

@@ -1,22 +1,22 @@
-import transformers
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "meta-llama/Llama-3.3-70B-Instruct"
+# Load Model dan Tokenizer
+model_name = "meta-llama/Llama-3.3-70B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
 
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model_id,
-    model_kwargs={"torch_dtype": torch.bfloat16},
-    device_map="auto",
-)
+# Fungsi Chatbot
+def chat(input_text):
+    # Tokenisasi input
+    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
+    # Hasilkan output menggunakan model
+    outputs = model.generate(**inputs, max_length=1000, top_p=0.9, temperature=0.7)
+    # Decode output menjadi teks
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-messages = [
-    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
-    {"role": "user", "content": "Who are you?"},
-]
-
-outputs = pipeline(
-    messages,
-    max_new_tokens=256,
-)
-print(outputs[0]["generated_text"][-1])
+# Membuat antarmuka Gradio
+iface = gr.Interface(fn=chat, inputs="text", outputs="text", live=True)
+iface.launch()