|
|
--- |
|
|
license: mit |
|
|
datasets: |
|
|
- datatab/SrpWikiDataset |
|
|
- datatab/open-orca-slim-serbian |
|
|
language: |
|
|
- sr |
|
|
base_model: |
|
|
- datatab/Yugo55A-GPT |
|
|
--- |
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
- **Developed by:** datatab |
|
|
- **License:** mit |
|
|
|
|
|
|
|
|
## 🏆 Results |
|
|
> Results obtained through the [**Serbian LLM Evaluation Benchmark**](https://huggingface.co/datasets/datatab/serbian-llm-benchmark) |
|
|
|
|
|
<table> |
|
|
<tr> |
|
|
<th><strong>MODEL<strong></th> |
|
|
<th><strong>ARC-E<strong></th> |
|
|
<th><strong>ARC-C<strong></th> |
|
|
<th><strong>Hellaswag<strong></th> |
|
|
<th><strong>PiQA<strong></th> |
|
|
<th><strong>Winogrande<strong></th> |
|
|
<th><strong>BoolQ<strong></th> |
|
|
<th><strong>OpenbookQA<strong></th> |
|
|
<th><strong>OZ_EVAL<strong></th> |
|
|
<th>SCORE</th> |
|
|
</tr> |
|
|
<tr> |
|
|
<td><a href="https://huggingface.co/datatab/YugoGPT-Florida/">YugoGPT-Florida</a></td> |
|
|
<td><strong>0.6918<strong></td> |
|
|
<td><strong>0.5766<strong></td> |
|
|
<td><strong>0.4037<strong></td> |
|
|
<td><strong>0.7374<strong></td> |
|
|
<td><strong>0.5782<strong></td> |
|
|
<td><strong>0.8685<strong></td> |
|
|
<td><strong>0.5918<strong></td> |
|
|
<td><strong>0.7407<strong></td> |
|
|
<td><strong>64,85875<strong></td> |
|
|
</tr> |
|
|
<tr> |
|
|
<td><a href="https://huggingface.co/datatab/Yugo55A-GPT/">Yugo55A-GPT</a></td> |
|
|
<td>0.5846</td> |
|
|
<td>0.5185</td> |
|
|
<td>0.3686</td> |
|
|
<td>0.7076</td> |
|
|
<td>0.5277</td> |
|
|
<td>0.8584</td> |
|
|
<td>0.5485</td> |
|
|
<td>0.6883</td> |
|
|
<td>60,0275</td> |
|
|
</tr> |
|
|
<tr> |
|
|
<td><a href="https://huggingface.co/datatab/Yugo60-GPT">Yugo60-GPT</a></td> |
|
|
<td>0.4948</td> |
|
|
<td>0.4542</td> |
|
|
<td>0.3342</td> |
|
|
<td>0.6897</td> |
|
|
<td>0.5138</td> |
|
|
<td>0.8212</td> |
|
|
<td>0.5155</td> |
|
|
<td>0.6379</td> |
|
|
<td>55,76625</td> |
|
|
</tr> |
|
|
<tr> |
|
|
<td><a href="https://huggingface.co/datatab/Yugo45-GPT">Yugo45-GPT</a></td> |
|
|
<td>0.4049</td> |
|
|
<td>0.3900</td> |
|
|
<td>0.2812</td> |
|
|
<td>0.6055</td> |
|
|
<td>0.4992</td> |
|
|
<td>0.5793</td> |
|
|
<td>0.4433</td> |
|
|
<td>0.6111</td> |
|
|
<td>47,68125</td> |
|
|
</tr> |
|
|
</table> |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
# 🏋️ Training Stats |
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
## 💻 Usage |
|
|
```terminal |
|
|
!pip -q install git+https://github.com/huggingface/transformers |
|
|
|
|
|
``` |
|
|
|
|
|
```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, MistralForCausalLM |
|
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
|
|
|
model = MistralForCausalLM.from_pretrained( |
|
|
"datatab/YugoGPT-Florida", |
|
|
torch_dtype="auto" |
|
|
).to(device) |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("datatab/YugoGPT-Florida") |
|
|
|
|
|
``` |
|
|
|
|
|
```python |
|
|
from typing import Optional |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer |
|
|
|
|
|
|
|
|
def generate( |
|
|
user_content: str, system_content: Optional[str] = "" |
|
|
) -> str: |
|
|
system_content = """Ispod se nalazi uputstvo koje definiše zadatak, zajedno sa unosom koji pruža dodatni kontekst. |
|
|
Na osnovu ovih informacija, napišite odgovor koji precizno i tačno ispunjava zahtev. |
|
|
""" |
|
|
|
|
|
messages = [ |
|
|
{ |
|
|
"role": "system", |
|
|
"content": system_content, |
|
|
}, |
|
|
{"role": "user", "content": user_content}, |
|
|
] |
|
|
|
|
|
tokenized_chat = tokenizer.apply_chat_template( |
|
|
messages, tokenize=True, add_generation_prompt=True, return_tensors="pt" |
|
|
).to("cuda") |
|
|
|
|
|
text_streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) |
|
|
output = model.generate( |
|
|
tokenized_chat, |
|
|
streamer=text_streamer, |
|
|
max_new_tokens=2048, |
|
|
temperature=0.1, |
|
|
repetition_penalty=1.11, |
|
|
top_p=0.92, |
|
|
top_k=1000, |
|
|
pad_token_id=tokenizer.pad_token_id, |
|
|
eos_token_id=tokenizer.eos_token_id, |
|
|
do_sample=True, |
|
|
) |
|
|
|
|
|
generated_text = tokenizer.decode(output[0], skip_special_tokens=True) |
|
|
|
|
|
``` |
|
|
|
|
|
```python |
|
|
generate("Nabroj mi sve planete suncevog sistemai reci mi koja je najveca planeta?") |
|
|
|
|
|
``` |
|
|
|
|
|
```terminal |
|
|
Sunčev sistem sadrži osam planeta: Merkur, Venera, Zemlja, Mars, Jupiter, Saturn, Uran i Neptun. Najveća planeta u Sunčevom sistemu je Jupiter. |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## 💡 Contributions Welcome! |
|
|
|
|
|
Have ideas, bug fixes, or want to add a custom model? We'd love for you to be part of the journey! Contributions help grow and enhance the capabilities of the **YugoGPT-Florida**. |
|
|
|
|
|
## 📜 Citation |
|
|
|
|
|
Thanks for using **YugoGPT-Florida** — where language learning models meet Serbian precision and creativity! Let's build smarter models together. 🚀� |
|
|
|
|
|
If you find this model useful in your research, please cite it as follows: |
|
|
|
|
|
```bibtex |
|
|
@article{YugoGPT-Florida}, |
|
|
title={YugoGPT-Florida}, |
|
|
author={datatab}, |
|
|
year={2024}, |
|
|
url={https://huggingface.co/datatab/YugoGPT-Florida} |
|
|
} |
|
|
``` |
|
|
|
|
|
|
|
|
<div id="zastava"> |
|
|
<div class="grb"> |
|
|
<img src="https://www.ai.gov.rs/img/logo_60x120-2.png" style="position:relative; left:30px; z-index:10; height:85px"> |
|
|
</div> |
|
|
<table width=100% style="border:0px"> |
|
|
<<tr style="background-color:#C6363C;width:100%;border:0px;height:30px"><td style="width:100vw"></td></tr> |
|
|
<tr style="background-color:#0C4076;width:100%;border:0px;height:30px"><td></td></tr> |
|
|
<tr style="background-color:#ffffff;width:100%;border:0px;height:30px"><td></td></tr> |
|
|
</table> |
|
|
</div> |
|
|
|
|
|
<style> |
|
|
.ffeat: { |
|
|
color:red |
|
|
} |
|
|
|
|
|
.cover { |
|
|
width: 100%; |
|
|
margin-bottom: 5pt |
|
|
} |
|
|
|
|
|
.highlight-container, .highlight { |
|
|
position: relative; |
|
|
text-decoration:none |
|
|
} |
|
|
|
|
|
.highlight-container { |
|
|
display: inline-block; |
|
|
|
|
|
} |
|
|
|
|
|
.highlight{ |
|
|
color:white; |
|
|
text-transform:uppercase; |
|
|
font-size: 16pt; |
|
|
} |
|
|
|
|
|
.highlight-container{ |
|
|
padding:5px 10px |
|
|
} |
|
|
|
|
|
.highlight-container:before { |
|
|
content: " "; |
|
|
display: block; |
|
|
height: 100%; |
|
|
width: 100%; |
|
|
margin-left: 0px; |
|
|
margin-right: 0px; |
|
|
position: absolute; |
|
|
background: #e80909; |
|
|
transform: rotate(2deg); |
|
|
top: -1px; |
|
|
left: -1px; |
|
|
border-radius: 20% 25% 20% 24%; |
|
|
padding: 10px 18px 18px 10px; |
|
|
} |
|
|
|
|
|
div.grb, #zastava>table { |
|
|
position:absolute; |
|
|
top:0px; |
|
|
left: 0px; |
|
|
margin:0px |
|
|
} |
|
|
|
|
|
div.grb>img, #zastava>table{ |
|
|
margin:0px |
|
|
} |
|
|
|
|
|
#zastava { |
|
|
position: relative; |
|
|
margin-bottom:120px |
|
|
} |
|
|
|
|
|
p { |
|
|
font-size:14pt |
|
|
} |
|
|
</style> |
