---
language:
- sr
license: mit
tags:
- text-generation-inference
- transformers
- mistral
base_model: datatab/Yugo55-GPT-v4
datasets:
- datatab/alpaca-cleaned-serbian-full
- datatab/open-orca-slim-serbian
---

# Yugo55-GPT-v4-4bit

- **Developed by:** datatab
- **License:** mit
- **Quantized from model :** datatab/Yugo55-GPT-v4

## 🧩 Configuration

```yaml
models:
  - model: datatab/Serbian-Mistral-Orca-Slim-v1
    parameters:
      weight: 1.0
  - model: mlabonne/AlphaMonarch-7B
    parameters:
      weight: 1.0
  - model: datatab/YugoGPT-Alpaca-v1-epoch1-good
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16
```

## 🏆 Results 
> Results obtained through the Serbian LLM evaluation, released by Aleksa Gordić: [serbian-llm-eval](https://github.com/gordicaleksa/serbian-llm-eval)
> * Evaluation was conducted on a 4-bit version of the model due to hardware resource constraints.

<table>
  <tr>
    <th>MODEL</th>
    <th>ARC-E</th>
    <th>ARC-C</th>
    <th>Hellaswag</th>
    <th>BoolQ</th>
    <th>Winogrande</th>
    <th>OpenbookQA</th>
    <th>PiQA</th>
  </tr>
  <tr>
    <td><a href="https://huggingface.co/datatab/Yugo55-GPT-v4-4bit/">*Yugo55-GPT-v4-4bit</a></td>
    <td>51.41</td>
    <td>36.00</td>
    <td>57.51</td>
    <td>80.92</td>
    <td><strong>65.75</strong></td>
    <td>34.70</td>
    <td><strong>70.54</strong></td>
  </tr>
  <tr>
    <td><a href="https://huggingface.co/datatab/Yugo55A-GPT/">Yugo55A-GPT</a></td>
    <td><strong>51.52</strong></td>
    <td><strong>37.78</strong></td>
    <td><strong>57.52</strong></td>
    <td><strong>84.40</strong></td>
    <td>65.43</td>
    <td><strong>35.60</strong></td>
    <td>69.43</td>
  </tr>
</table>



## 💻 Usage
```terminal
!pip -q install git+https://github.com/huggingface/transformers # need to install from github
!pip install -q datasets loralib sentencepiece
!pip -q install bitsandbytes accelerate
```

```python
from IPython.display import HTML, display

def set_css():
  display(HTML('''
  <style>
    pre {
        white-space: pre-wrap;
    }
  </style>
  '''))
get_ipython().events.register('pre_run_cell', set_css)

```

```python
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
)

tokenizer = AutoTokenizer.from_pretrained(
    "datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
)


```

```python
from transformers import TextStreamer


def generate(question="", input="Odgovaraj uvek na Srpskom jeziku!!!"):
    alpaca_prompt = """Ispod je uputstvo koje opisuje zadatak, upareno sa unosom koji pruža dodatni kontekst. Napišite odgovor koji na odgovarajući način kompletira zahtev.
  
  ### Uputstvo:
   {}
  ### Unos:
   {}
  ### Odgovor:
   {}"""

    inputs = tokenizer(
        [
            alpaca_prompt.format(
                question,  # instruction
                input,  # input
                "",  # output - leave this blank for generation!
            )
        ],
        return_tensors="pt",
    ).to("cuda")

    text_streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
    _ = model.generate(
        **inputs,
        streamer=text_streamer,
        max_new_tokens=1024,
        temperature=0.1,
        repetition_penalty=1.11,
        top_p=0.92,
        top_k=1,
        pad_token_id=tokenizer.pad_token_id,
        eos_token_id=tokenizer.eos_token_id,
        do_sample=True,
        use_cache=True
    )

```

```python
generate("Nabroj mi sve planete suncevog sistemai reci mi koja je najveca planeta")
```

```python
generate("Koja je razlika između lame, vikune i alpake?")
```

```python
generate("Napišite kratku e-poruku Semu Altmanu dajući razloge za GPT-4 otvorenog koda")
```