Update app.py

app.py

@@ -1,25 +1,8 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
-device = "cpu" # the device to load the model onto
+# Use a pipeline as a high-level helper
+from transformers import pipeline
 
-model = AutoModelForCausalLM.from_pretrained(
-    "NTQAI/Nxcode-CQ-7B-orpo",
-    torch_dtype="auto",
-    device_map="auto"
-)
-tokenizer = AutoTokenizer.from_pretrained("NTQAI/Nxcode-CQ-7B-orpo")
-
-prompt = """Complete the following Python function:
-from typing import List
-
-
-def has_close_elements(numbers: List[float], threshold: float) -> bool:
-
- 
-"""
 messages = [
-    {"role": "user", "content": prompt}
+    {"role": "user", "content": "Who are you?"},
 ]
-
-inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
-outputs = model.generate(inputs, max_new_tokens=512, do_sample=True, top_k=50, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
-res = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
+pipe = pipeline("text-generation", model="defog/llama-3-sqlcoder-8b")
+pipe(messages)