Update app.py

app.py

@@ -1,37 +1,8 @@
-# Install necessary libraries
-# !pip install transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-import torch
-
-# Model and prompt details
 model_name = "mlabonne/llama-2-7b-guanaco"
-prompt = "What is a large language model?"
-
-# Load tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.float16,
-    device_map="auto",
-    offload_folder="offload/folder"  # Replace with the path to the offload folder
-)
-
-# Generate text using the provided prompt
-sequences = pipeline(
-    "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-    device=0,  # Change to the appropriate device index or "cuda" if using GPU
-)(
-    f'<s>[INST] {prompt} [/INST]',
-    do_sample=True,
-    top_k=10,
-    num_return_sequences=1,
-    eos_token_id=tokenizer.eos_token_id,
-    max_length=200,
-)
 
-# Print the generated text
-for seq in sequences:
-    print(f"Generated Text: {seq['generated_text']}")
+try:
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+except Exception as e:
+    print(f"Error loading the model: {e}")