!pip install transformers peft accelerate bitsandbytes

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model = AutoPeftModelForCausalLM.from_pretrained(
    "Mollel/Gemma_Swahili_Mollel_1_epoch",
    load_in_4bit = False
)

tokenizer = AutoTokenizer.from_pretrained("Mollel/Gemma_Swahili_Mollel_1_epoch")


input_prompt = """
### Instruction:
{}

### Input:
{}

### Response:
{}"""



input_text = input_prompt.format(
        "Andika aya fupi kuhusu mada iliyotolewa.", # instruction
        "Umuhimu wa kutumia nishati inayoweza kurejeshwa", # input
        "", # output - leave this blank for generation!
    )

inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)
response = tokenizer.batch_decode(outputs)[0]

print(response)