Update app.py

app.py

@@ -1,7 +1,11 @@
-from transformers import pipeline
+from transformers import AutoTokenizer, LlamaForCausalLM
 
-classifier = pipeline("sentiment-analysis")
+model = LlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
+tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
 
-res = classifier("I've been waiting for a HuggingFace cours my whole life.")
+prompt = "Hey, are you conscious? Can you talk to me?"
+inputs = tokenizer(prompt, return_tensors="pt")
 
-print(res)
+# Generate
+generate_ids = model.generate(inputs.input_ids, max_length=30)
+tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]