Update app.py

app.py

@@ -1,10 +1,10 @@
-from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
-messages=[
-    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
-]
-inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
-# tokenizer.eos_token_id is the id of <|EOT|> token
-outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
-print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
+import transformers
+import torch
+
+model_id = "meta-llama/Llama-3.1-8B"
+
+pipeline = transformers.pipeline(
+    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
+)
+
+pipeline("Hey how are you doing today?")