Update app.py

app.py

@@ -1,8 +1,10 @@
-# Use a pipeline as a high-level helper
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-messages = [
-    {"role": "user", "content": "Who are you?"},
-]
-pipe = pipeline("text-generation", model="pentagoniac/SEMIKONG-8b-GPTQ ")
-pipe(messages)
+MODEL_DIR = "pentagoniac/SEMIKONG-8B"
+model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False)
+
+input_text = "what is semiconductor ?"
+inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_length=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))