---
license: cc-by-nc-4.0
language:
- ro
base_model:
- OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09
datasets:
- OpenLLM-Ro/ro_dpo_helpsteer
model-index:
- name: OpenLLM-Ro/RoGemma2-9b-Instruct-DPO-2024-10-09
results:
- task:
type: text-generation
dataset:
name: RoMT-Bench
type: RoMT-Bench
metrics:
- name: Score
type: Score
value: 6.77
- task:
type: text-generation
dataset:
name: RoCulturaBench
type: RoCulturaBench
metrics:
- name: Score
type: Score
value: 4.83
- task:
type: text-generation
dataset:
name: Romanian_Academic_Benchmarks
type: Romanian_Academic_Benchmarks
metrics:
- name: Average accuracy
type: accuracy
value: 59.08
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_arc_challenge
type: OpenLLM-Ro/ro_arc_challenge
metrics:
- name: Average accuracy
type: accuracy
value: 54.10
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_mmlu
type: OpenLLM-Ro/ro_mmlu
metrics:
- name: Average accuracy
type: accuracy
value: 63.41
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_winogrande
type: OpenLLM-Ro/ro_winogrande
metrics:
- name: Average accuracy
type: accuracy
value: 70.02
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_hellaswag
type: OpenLLM-Ro/ro_hellaswag
metrics:
- name: Average accuracy
type: accuracy
value: 59.35
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_gsm8k
type: OpenLLM-Ro/ro_gsm8k
metrics:
- name: Average accuracy
type: accuracy
value: 57.24
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_truthfulqa
type: OpenLLM-Ro/ro_truthfulqa
metrics:
- name: Average accuracy
type: accuracy
value: 50.39
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary
type: LaRoSeDa_binary
metrics:
- name: Average macro-f1
type: macro-f1
value: 97.74
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass
type: LaRoSeDa_multiclass
metrics:
- name: Average macro-f1
type: macro-f1
value: 67.40
- task:
type: text-generation
dataset:
name: WMT_EN-RO
type: WMT_EN-RO
metrics:
- name: Average bleu
type: bleu
value: 27.32
- task:
type: text-generation
dataset:
name: WMT_RO-EN
type: WMT_RO-EN
metrics:
- name: Average bleu
type: bleu
value: 15.96
- task:
type: text-generation
dataset:
name: XQuAD
type: XQuAD
metrics:
- name: Average exact_match
type: exact_match
value: 32.42
- task:
type: text-generation
dataset:
name: XQuAD
type: XQuAD
metrics:
- name: Average f1
type: f1
value: 58.68
- task:
type: text-generation
dataset:
name: STS
type: STS
metrics:
- name: Average spearman
type: spearman
value: 80.82
- task:
type: text-generation
dataset:
name: STS
type: STS
metrics:
- name: Average pearson
type: pearson
value: 81.50
- task:
type: text-generation
dataset:
name: RoMT-Bench
type: RoMT-Bench
metrics:
- name: First turn
type: Score
value: 7.24
- name: Second turn
type: Score
value: 6.30
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_arc_challenge
type: OpenLLM-Ro/ro_arc_challenge
metrics:
- name: 0-shot
type: accuracy
value: 51.59
- name: 1-shot
type: accuracy
value: 50.99
- name: 3-shot
type: accuracy
value: 53.47
- name: 5-shot
type: accuracy
value: 54.84
- name: 10-shot
type: accuracy
value: 58.10
- name: 25-shot
type: accuracy
value: 55.61
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_mmlu
type: OpenLLM-Ro/ro_mmlu
metrics:
- name: 0-shot
type: accuracy
value: 62.15
- name: 1-shot
type: accuracy
value: 62.78
- name: 3-shot
type: accuracy
value: 64.27
- name: 5-shot
type: accuracy
value: 64.43
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_winogrande
type: OpenLLM-Ro/ro_winogrande
metrics:
- name: 0-shot
type: accuracy
value: 66.69
- name: 1-shot
type: accuracy
value: 68.82
- name: 3-shot
type: accuracy
value: 71.82
- name: 5-shot
type: accuracy
value: 72.77
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_hellaswag
type: OpenLLM-Ro/ro_hellaswag
metrics:
- name: 0-shot
type: accuracy
value: 56.98
- name: 1-shot
type: accuracy
value: 57.73
- name: 3-shot
type: accuracy
value: 59.29
- name: 5-shot
type: accuracy
value: 60.70
- name: 10-shot
type: accuracy
value: 62.03
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_gsm8k
type: OpenLLM-Ro/ro_gsm8k
metrics:
- name: 1-shot
type: accuracy
value: 46.78
- name: 3-shot
type: accuracy
value: 59.97
- name: 5-shot
type: accuracy
value: 64.97
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary
type: LaRoSeDa_binary
metrics:
- name: 0-shot
type: macro-f1
value: 97.30
- name: 1-shot
type: macro-f1
value: 97.50
- name: 3-shot
type: macro-f1
value: 97.83
- name: 5-shot
type: macro-f1
value: 98.33
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass
type: LaRoSeDa_multiclass
metrics:
- name: 0-shot
type: macro-f1
value: 59.30
- name: 1-shot
type: macro-f1
value: 65.52
- name: 3-shot
type: macro-f1
value: 70.94
- name: 5-shot
type: macro-f1
value: 73.85
- task:
type: text-generation
dataset:
name: WMT_EN-RO
type: WMT_EN-RO
metrics:
- name: 0-shot
type: bleu
value: 17.49
- name: 1-shot
type: bleu
value: 30.33
- name: 3-shot
type: bleu
value: 30.58
- name: 5-shot
type: bleu
value: 30.88
- task:
type: text-generation
dataset:
name: WMT_RO-EN
type: WMT_RO-EN
metrics:
- name: 0-shot
type: bleu
value: 2.17
- name: 1-shot
type: bleu
value: 10.69
- name: 3-shot
type: bleu
value: 21.68
- name: 5-shot
type: bleu
value: 29.28
- task:
type: text-generation
dataset:
name: XQuAD_EM
type: XQuAD_EM
metrics:
- name: 0-shot
type: exact_match
value: 23.28
- name: 1-shot
type: exact_match
value: 33.45
- name: 3-shot
type: exact_match
value: 34.37
- name: 5-shot
type: exact_match
value: 38.57
- task:
type: text-generation
dataset:
name: XQuAD_F1
type: XQuAD_F1
metrics:
- name: 0-shot
type: f1
value: 47.16
- name: 1-shot
type: f1
value: 60.28
- name: 3-shot
type: f1
value: 62.09
- name: 5-shot
type: f1
value: 65.20
- task:
type: text-generation
dataset:
name: STS_Spearman
type: STS_Spearman
metrics:
- name: 1-shot
type: spearman
value: 75.34
- name: 3-shot
type: spearman
value: 82.71
- name: 5-shot
type: spearman
value: 84.41
- task:
type: text-generation
dataset:
name: STS_Pearson
type: STS_Pearson
metrics:
- name: 1-shot
type: pearson
value: 77.97
- name: 3-shot
type: pearson
value: 82.49
- name: 5-shot
type: pearson
value: 84.05
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This model points/is identical to [RoGemma2-9b-Instruct-DPO-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-DPO-2024-10-09).
RoGemma2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **human aligned instruct 9B model**. Links to other models can be found at the bottom of this page.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
OpenLLM-Ro represents the first open-source effort to build a LLM specialized for Romanian. OpenLLM-Ro developed and publicly releases a collection of Romanian LLMs, both in the form of foundational model and instruct and chat variants.
- **Developed by:** OpenLLM-Ro
<!-- - **Funded by [optional]:** [More Information Needed] -->
<!-- - **Shared by [optional]:** [More Information Needed] -->
<!-- - **Model type:** [More Information Needed] -->
- **Language(s):** Romanian
- **License:** cc-by-nc-4.0
- **Finetuned from model:** [RoGemma2-9b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09)
- **Trained using:** [RoHelpSteer](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_helpsteer)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/OpenLLM-Ro/LLaMA-Factory
- **Paper:** https://arxiv.org/abs/2406.18266
## Intended Use
### Intended Use Cases
RoGemma2 is intented for research use in Romanian. Base models can be adapted for a variety of natural language tasks while instruction and chat tuned models are intended for assistant-like chat.
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
Use in any manner that violates the license, any applicable laws or regluations, use in languages other than Romanian.
## How to Get Started with the Model
Use the code below to get started with the model.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoGemma2-9b-Instruct-DPO")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoGemma2-9b-Instruct-DPO")
instruction = "Ce jocuri de societate pot juca cu prietenii mei?"
chat = [
{"role": "user", "content": instruction},
]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, system_message="")
inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0]))
```
## Academic Benchmarks
<table>
<tbody>
<tr>
<td><strong>Model</strong></td>
<td><strong><center>Average</center></strong></td>
<td><strong><center>ARC</center></strong></td>
<td><strong><center>MMLU</center></strong></td>
<td><strong><center>Winogrande</center></strong></td>
<td><strong><center>Hellaswag</center></strong></td>
<td><strong><center>GSM8k</center></strong></td>
<td><strong><center>TruthfulQA</center></strong></td>
</tr>
<tr>
<td>gemma-2-9b-it</td><td><center>56.22</center></td><td><center>50.33</center></td><td><center><strong>64.01</strong></center></td><td><center>64.88</center></td><td><center><strong>63.11</strong></center></td><td><center>41.95</center></td><td><center>53.03</center></td>
</tr>
<tr>
<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>57.06</center></td><td><center><strong>56.20</strong></center></td><td><center>62.98</center></td><td><center><strong>71.00</strong></center></td><td><center>60.52</center></td><td><center>37.86</center></td><td><center><strong>53.77</strong></center></td>
</tr>
<tr>
<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em><strong>59.08</strong></em></center></td><td><center><em>54.10</em></center></td><td><center><em>63.41</em></center></td><td><center><em>70.02</em></center></td><td><center><em>59.35</em></center></td><td><center><em><strong>57.24</strong></em></center></td><td><center><em>50.39</em></center></td>
</tr>
</tbody>
</table>
## Downstream tasks
<table>
<tbody>
<tr>
<td></td>
<td colspan="4"><center><strong>LaRoSeDa</strong></center></td>
<td colspan="4"><center><strong>WMT</strong></center></td>
</tr>
<tr>
<td></td>
<td colspan="2"><center><strong>Few-shot</strong></center></td>
<td colspan="2"><center><strong>Finetuned</strong></center></td>
<td colspan="2"><center><strong>Few-shot</strong></center></td>
<td colspan="2"><center><strong>Finetuned</strong></center></td>
</tr>
<tr>
<td><strong>Model</strong></td>
<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
<td><center><strong>RO-EN<br>(Bleu)</strong></center></td>
<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
<td><center><strong>RO-EN<br>(Bleu)</strong></center>
</tr>
<tr>
<td>gemma-2-9b-it</td><td><center>90.82</center></td><td><center>52.51</center></td><td><center><strong>98.97</strong></center></td><td><center>86.02</center></td><td><center>19.97</center></td><td><center><strong>28.94</strong></center></td><td><center>27.94</center></td><td><center><strong>41.61</strong></center></td>
</tr>
<tr>
<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>96.19</center></td><td><center>62.49</center></td><td><center>98.93</center></td><td><center><strong>88.33</strong></center></td><td><center>25.74</center></td><td><center>23.16</center></td><td><center><strong>28.43</strong></center></td><td><center>40.94</center></td>
</tr>
<tr>
<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em><strong>97.74</strong></em></center></td><td><center><em><strong>67.40</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>27.32</strong></em></center></td><td><center><em>15.96</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
</tr>
</tbody>
</table>
<table>
<tbody>
<tr>
<td></td>
<td colspan="4"><center><strong>XQuAD</strong></center></td>
<td colspan="4"><center><strong>STS</strong></center></td>
</tr>
<tr>
<td></td>
<td colspan="2"><center><strong>Few-shot</strong></center></td>
<td colspan="2"><center><strong>Finetuned</strong></center></td>
<td colspan="2"><center><strong>Few-shot</strong></center></td>
<td colspan="2"><center><strong>Finetuned</strong></center></td>
</tr>
<tr>
<td><strong>Model</strong></td>
<td><center><strong>(EM)</strong></center></td>
<td><center><strong>(F1)</strong></center></td>
<td><center><strong>(EM)</strong></center></td>
<td><center><strong>(F1)</strong></center></td>
<td><center><strong>(Spearman)</strong></center></td>
<td><center><strong>(Pearson)</strong></center></td>
<td><center><strong>(Spearman)</strong></center></td>
<td><center><strong>(Pearson)</strong></center></td>
</tr>
<tr>
<td>gemma-2-9b-it</td><td><center>37.56</center></td><td><center>57.48</center></td><td><center><strong>71.09</strong></center></td><td><center><strong>84.78</strong></center></td><td><center>71.39</center></td><td><center>71.73</center></td><td><center>89.07</center></td><td><center>89.29</center></td>
</tr>
<tr>
<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center><strong>51.37</strong></center></td><td><center><strong>70.74</strong></center></td><td><center>50.00</center></td><td><center>64.10</center></td><td><center>77.15</center></td><td><center>77.10</center></td><td><center><strong>89.45</strong></center></td><td><center><strong>89.89</strong></center></td>
</tr>
<tr>
<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em>32.42</em></center></td><td><center><em>58.68</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>80.82</strong></em></center></td><td><center><em><strong>81.50</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
</tr>
</tbody>
</table>
## MT-Bench
<table>
<tbody>
<tr>
<td><strong>Model</strong></td>
<td><strong><center>Average</center></strong></td>
<td><strong><center>1st turn</center></strong></td>
<td><strong><center>2nd turn</center></strong></td>
<td><strong><center>Answers in Ro</center></strong></td>
</tr>
<tr>
<td>gemma-2-9b-it</td><td><center><strong>7.50</strong></center></td><td><center><strong>7.91</strong></center></td><td><center><strong>7.09</strong></center></td><td><center>159/160</center></td>
</tr>
<tr>
<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>6.08</center></td><td><center>6.78</center></td><td><center>5.39</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em>6.77</em></center></td><td><center><em>7.24</em></center></td><td><center><em>6.30</em></center></td><td><center><em><strong>160/160</strong></em></center></td>
</tr>
</tbody>
</table>
## RoCulturaBench
<table>
<tbody>
<tr>
<td><strong>Model</strong></td>
<td><strong><center>Average</center></strong></td>
<td><strong><center>Answers in Ro</center></strong></td>
</tr>
<tr>
<td>gemma-2-9b-it</td><td><center><strong>5.68</strong></center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>4.20</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em>4.83</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
</tr>
</tbody>
</table>
## RoGemma2 Model Family
| Model | Link |
|--------------------|:--------:|
|RoGemma2-9b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09) |
|*RoGemma2-9b-Instruct-DPO-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-DPO-2024-10-09) |
## Citation
```
@misc{masala2024vorbecstiromanecsterecipetrain,
title={"Vorbe\c{s}ti Rom\^ane\c{s}te?" A Recipe to Train Powerful Romanian LLMs with English Instructions},
author={Mihai Masala and Denis C. Ilie-Ablachim and Alexandru Dima and Dragos Corlatescu and Miruna Zavelca and Ovio Olaru and Simina Terian-Dan and Andrei Terian-Dan and Marius Leordeanu and Horia Velicu and Marius Popescu and Mihai Dascalu and Traian Rebedea},
year={2024},
eprint={2406.18266},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2406.18266},
}
```
<!-- **APA:**
[More Information Needed] -->