from transformers import BloomTokenizerFast, BloomForCausalLM, pipeline


text="اكتب مقالا من عدة أسطر عن الذكاء الصناعي وتطوراته"
prompt = f'Instruction:\n{text}\n\nResponse:'

model = BloomForCausalLM.from_pretrained('Naseej/noon-7b')

tokenizer = BloomTokenizerFast.from_pretrained('Naseej/noon-7b')

generation_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)

# We recommend the provided hyperparameters for generation
# But encourage you to try different values
response = generation_pipeline(prompt,
    pad_token_id=tokenizer.eos_token_id,
    do_sample=False,
    num_beams=4,
    max_length=500,
    top_p=0.1,
    top_k=20,
    repetition_penalty = 3.0,
    no_repeat_ngram_size=3)[0]['generated_text']

print(response)