app.py

# Install necessary libraries
# !pip install transformers

from transformers import AutoTokenizer, pipeline
import torch

# Model and prompt details
model_name = "mlabonne/llama-2-7b-guanaco"
prompt = "What is a large language model?"

# Load tokenizer and pipeline
tokenizer = AutoTokenizer.from_pretrained(model_name)
text_generation_pipeline = pipeline(
    "text-generation",
    model=model_name,
    torch_dtype=torch.float16,
    device_map="auto",
)

# Generate text using the provided prompt
sequences = text_generation_pipeline(
    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']}")