# Your Model Name

This model is LLama 3.1 8B finetuned using bahasa indonesia datasets.

## Model Details

- **Architecture**: LLama 3.1 8B
- **Dataset**: rubythalib33/alpaca-cleaned-translated-id
- **Fine-tuning**: using QLoRA from unsloth to finetune it

## Usage

```python

alpaca_prompt = "Di bawah ini adalah instruksi yang menjelaskan tugas, dipasangkan dengan masukan yang memberikan konteks lebih lanjut. Tulis tanggapan yang melengkapi permintaan dengan tepat.

### Instruction:
#change this with curly braces

### Input:
#change this with curly braces

### Response:
#change this with curly braces

from unsloth import FastLanguageModel
    model, tokenizer = FastLanguageModel.from_pretrained(
        model_name = "rubythalib33/llama3_1_8b_finetuned_bahasa_indonesia", # YOUR MODEL YOU USED FOR TRAINING
        max_seq_length = max_seq_length,
        dtype = dtype,
        load_in_4bit = load_in_4bit,
    )
    FastLanguageModel.for_inference(model)

inputs = tokenizer(
[
    alpaca_prompt.format(
        "coba lanjutkan bilangan fibbonaci dibawah dalam bentuk list", # instruction
        "[1,1,2,3]", # input
        "[1,1,2,3,", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = max_new_tokens)