Update app.py

app.py

@@ -7,13 +7,14 @@ hf_token = os.environ.get("HF_HOME", None)
 
 # Load the model and tokenizer
 model_name = "meta-llama/CodeLlama-7b-hf"
-model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token, torch_dtype="float16", device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
 
 
 def generate_code(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(inputs["input_ids"], max_length=200)
+    batch_size = 1
+    inputs = tokenizer(input_texts, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    outputs = model.generate(inputs['input_ids'], max_length=512, num_return_sequences=batch_size)
     code = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return code