---
license: cc-by-nc-4.0
language:
- ro
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- OpenLLM-Ro/ro_sft_alpaca
- OpenLLM-Ro/ro_sft_alpaca_gpt4
- OpenLLM-Ro/ro_sft_dolly
- OpenLLM-Ro/ro_sft_selfinstruct_gpt4
- OpenLLM-Ro/ro_sft_norobots
- OpenLLM-Ro/ro_sft_orca
- OpenLLM-Ro/ro_sft_camel
- OpenLLM-Ro/ro_sft_oasst
- OpenLLM-Ro/ro_sft_ultrachat
model-index:
    - name: OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09
      results:
        - task:
            type: text-generation
          dataset:
            name: RoMT-Bench
            type: RoMT-Bench
          metrics:
            - name: Score
              type: Score
              value: 5.38
        - task:
            type: text-generation
          dataset:
            name: RoCulturaBench
            type: RoCulturaBench
          metrics:
            - name: Score
              type: Score
              value: 3.81
        - task:
            type: text-generation
          dataset:
            name: Romanian_Academic_Benchmarks
            type: Romanian_Academic_Benchmarks
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 52.21
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_arc_challenge
            type: OpenLLM-Ro/ro_arc_challenge
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 47.94
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_mmlu
            type: OpenLLM-Ro/ro_mmlu
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 53.50
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_winogrande
            type: OpenLLM-Ro/ro_winogrande
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 66.06
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_hellaswag
            type: OpenLLM-Ro/ro_hellaswag
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 59.72
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_gsm8k
            type: OpenLLM-Ro/ro_gsm8k
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 40.16
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_truthfulqa
            type: OpenLLM-Ro/ro_truthfulqa
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 45.90
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_binary
            type: LaRoSeDa_binary
          metrics:
            - name: Average macro-f1
              type: macro-f1
              value: 95.58
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_multiclass
            type: LaRoSeDa_multiclass
          metrics:
            - name: Average macro-f1
              type: macro-f1
              value: 61.20
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_binary_finetuned
            type: LaRoSeDa_binary_finetuned
          metrics:
            - name: Average macro-f1
              type: macro-f1
              value: 96.46
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_multiclass_finetuned
            type: LaRoSeDa_multiclass_finetuned
          metrics:
            - name: Average macro-f1
              type: macro-f1
              value: 87.26
        - task:
            type: text-generation
          dataset:
            name: WMT_EN-RO
            type: WMT_EN-RO
          metrics:
            - name: Average bleu
              type: bleu
              value: 22.92
        - task:
            type: text-generation
          dataset:
            name: WMT_RO-EN
            type: WMT_RO-EN
          metrics:
            - name: Average bleu
              type: bleu
              value: 24.28
        - task:
            type: text-generation
          dataset:
            name: WMT_EN-RO_finetuned
            type: WMT_EN-RO_finetuned
          metrics:
            - name: Average bleu
              type: bleu
              value: 27.31
        - task:
            type: text-generation
          dataset:
            name: WMT_RO-EN_finetuned
            type: WMT_RO-EN_finetuned
          metrics:
            - name: Average bleu
              type: bleu
              value: 40.52
        - task:
            type: text-generation
          dataset:
            name: XQuAD
            type: XQuAD
          metrics:
            - name: Average exact_match
              type: exact_match
              value: 18.89
        - task:
            type: text-generation
          dataset:
            name: XQuAD
            type: XQuAD
          metrics:
            - name: Average f1
              type: f1
              value: 31.79
        - task:
            type: text-generation
          dataset:
            name: XQuAD_finetuned
            type: XQuAD_finetuned
          metrics:
            - name: Average exact_match
              type: exact_match
              value: 50.84
        - task:
            type: text-generation
          dataset:
            name: XQuAD_finetuned
            type: XQuAD_finetuned
          metrics:
            - name: Average f1
              type: f1
              value: 65.18
        - task:
            type: text-generation
          dataset:
            name: STS
            type: STS
          metrics:
            - name: Average spearman
              type: spearman
              value: 77.60
        - task:
            type: text-generation
          dataset:
            name: STS
            type: STS
          metrics:
            - name: Average pearson
              type: pearson
              value: 76.86
        - task:
            type: text-generation
          dataset:
            name: STS_finetuned
            type: STS_finetuned
          metrics:
            - name: Average spearman
              type: spearman
              value: 86.70
        - task:
            type: text-generation
          dataset:
            name: STS_finetuned
            type: STS_finetuned
          metrics:
            - name: Average pearson
              type: pearson
              value: 87.09
        - task:
            type: text-generation
          dataset:
            name: RoMT-Bench
            type: RoMT-Bench
          metrics:
            - name: First turn
              type: Score
              value: 6.09
            - name: Second turn
              type: Score
              value: 4.67
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_arc_challenge
            type: OpenLLM-Ro/ro_arc_challenge
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 46.02
            - name: 1-shot 
              type: accuracy
              value: 47.39
            - name: 3-shot 
              type: accuracy
              value: 47.73
            - name: 5-shot 
              type: accuracy
              value: 48.24
            - name: 10-shot 
              type: accuracy
              value: 48.33
            - name: 25-shot 
              type: accuracy
              value: 49.96
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_mmlu
            type: OpenLLM-Ro/ro_mmlu
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 51.19
            - name: 1-shot 
              type: accuracy
              value: 53.05
            - name: 3-shot 
              type: accuracy
              value: 54.83
            - name: 5-shot 
              type: accuracy
              value: 54.93
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_winogrande
            type: OpenLLM-Ro/ro_winogrande
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 64.09
            - name: 1-shot 
              type: accuracy
              value: 66.22
            - name: 3-shot 
              type: accuracy
              value: 66.61
            - name: 5-shot 
              type: accuracy
              value: 67.32
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_hellaswag
            type: OpenLLM-Ro/ro_hellaswag
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 59.34
            - name: 1-shot 
              type: accuracy
              value: 59.52
            - name: 3-shot 
              type: accuracy
              value: 59.61
            - name: 5-shot 
              type: accuracy
              value: 59.95
            - name: 10-shot 
              type: accuracy
              value: 60.19
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_gsm8k
            type: OpenLLM-Ro/ro_gsm8k
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 31.31
            - name: 1-shot 
              type: accuracy
              value: 42.23
            - name: 3-shot 
              type: accuracy
              value: 46.93
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_binary
            type: LaRoSeDa_binary
          metrics:
            - name: 0-shot 
              type: macro-f1
              value: 92.43
            - name: 1-shot 
              type: macro-f1
              value: 96.23
            - name: 3-shot 
              type: macro-f1
              value: 96.66
            - name: 5-shot 
              type: macro-f1
              value: 97.00
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_multiclass
            type: LaRoSeDa_multiclass
          metrics:
            - name: 0-shot 
              type: macro-f1
              value: 61.47
            - name: 1-shot 
              type: macro-f1
              value: 63.77
            - name: 3-shot 
              type: macro-f1
              value: 57.12
            - name: 5-shot 
              type: macro-f1
              value: 62.43
        - task:
            type: text-generation
          dataset:
            name: WMT_EN-RO
            type: WMT_EN-RO
          metrics:
            - name: 0-shot 
              type: bleu
              value: 5.25
            - name: 1-shot 
              type: bleu
              value: 28.62
            - name: 3-shot 
              type: bleu
              value: 29.60
            - name: 5-shot 
              type: bleu
              value: 28.21
        - task:
            type: text-generation
          dataset:
            name: WMT_RO-EN
            type: WMT_RO-EN
          metrics:
            - name: 0-shot 
              type: bleu
              value: 1.95
            - name: 1-shot 
              type: bleu
              value: 24.00
            - name: 3-shot 
              type: bleu
              value: 34.87
            - name: 5-shot 
              type: bleu
              value: 36.31
        - task:
            type: text-generation
          dataset:
            name: XQuAD_EM
            type: XQuAD_EM
          metrics:
            - name: 0-shot 
              type: exact_match
              value: 16.97
            - name: 1-shot 
              type: exact_match
              value: 31.01
            - name: 3-shot 
              type: exact_match
              value: 13.95
            - name: 5-shot 
              type: exact_match
              value: 13.61
        - task:
            type: text-generation
          dataset:
            name: XQuAD_F1
            type: XQuAD_F1
          metrics:
            - name: 0-shot 
              type: f1
              value: 31.29
            - name: 1-shot 
              type: f1
              value: 42.77
            - name: 3-shot 
              type: f1
              value: 24.78
            - name: 5-shot 
              type: f1
              value: 28.30
        - task:
            type: text-generation
          dataset:
            name: STS
            type: STS
          metrics:
            - name: 0-shot 
              type: spearman
              value: 77.73
            - name: 1-shot 
              type: spearman
              value: 76.78
            - name: 3-shot 
              type: spearman
              value: 78.30
        - task:
            type: text-generation
          dataset:
            name: STS
            type: STS
          metrics:
            - name: 0-shot 
              type: pearson
              value: 77.25
            - name: 1-shot 
              type: pearson
              value: 75.83
            - name: 3-shot 
              type: pearson
              value: 77.49

---

# Model Card for Model ID

*Built with Meta Llama 3*

This model points/is identical to [RoLlama3-8b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09).

<!-- Provide a quick summary of what the model is/does. -->

RoLlama3 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **instruct 8B 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:** [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
- **Trained using:** [RoAlpaca](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_alpaca), [RoAlpacaGPT4](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_alpaca_gpt4), [RoDolly](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_dolly), [RoSelfInstruct](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_selfinstruct_gpt4), [RoNoRobots](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_norobots), [RoOrca](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_orca), [RoCamel](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_camel), [RoOpenAssistant](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_oasst), [RoUltraChat](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_ultrachat)


### 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

RoLlama3 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/RoLlama3-8b-Instruct-2024-10-09")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09")

instruction = "Ce jocuri de societate pot juca cu prietenii mei?"
chat = [
        {"role": "system", "content": "Ești un asistent folositor, respectuos și onest. Încearcă să ajuți cât mai mult prin informațiile oferite, excluzând răspunsuri toxice, rasiste, sexiste, periculoase și ilegale."},
        {"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>Llama-3-8B-Instruct</td><td><center>50.62</center></td><td><center>43.69</center></td><td><center>52.04</center></td><td><center>59.33</center></td><td><center>53.19</center></td><td><center><strong>43.87</strong></center></td><td><center><strong>51.59</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>50.56</center></td><td><center>44.70</center></td><td><center>52.19</center></td><td><center><strong>67.23</strong></center></td><td><center>57.69</center></td><td><center>30.23</center></td><td><center>51.34</center></td>
</tr>
<tr>
<td><em>RoLlama3-8b-Instruct-2024-10-09</em></td><td><center><em><strong>52.21</strong></em></center></td><td><center><em><strong>47.94</strong></em></center></td><td><center><em><strong>53.50</strong></em></center></td><td><center><em>66.06</em></center></td><td><center><em><strong>59.72</strong></em></center></td><td><center><em>40.16</em></center></td><td><center><em>45.90</em></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>49.96</center></td><td><center>46.29</center></td><td><center>53.29</center></td><td><center>65.57</center></td><td><center>58.15</center></td><td><center>34.77</center></td><td><center>41.70</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>Llama-3-8B-Instruct</td><td><center>95.88</center></td><td><center>56.21</center></td><td><center><strong>98.53</strong></center></td><td><center>86.19</center></td><td><center>18.88</center></td><td><center><strong>30.98</strong></center></td><td><center><strong>28.02</strong></center></td><td><center>40.28</center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center><strong>97.52</strong></center></td><td><center><strong>67.41</strong></center></td><td><center>94.15</center></td><td><center>87.13</center></td><td><center><strong>24.01</strong></center></td><td><center>27.36</center></td><td><center>26.53</center></td><td><center>40.36</center></td>
</tr>
<tr>
<td><em>RoLlama3-8b-Instruct-2024-10-09</em></td><td><center><em>95.58</em></center></td><td><center><em>61.20</em></center></td><td><center><em>96.46</em></center></td><td><center><em><strong>87.26</strong></em></center></td><td><center><em>22.92</em></center></td><td><center><em>24.28</em></center></td><td><center><em>27.31</em></center></td><td><center><em><strong>40.52</strong></em></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>97.48</center></td><td><center>54.00</center></td><td><center>-</center></td><td><center>-</center></td><td><center>22.09</center></td><td><center>23.00</center></td><td><center>-</center></td><td><center>-</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>Llama-3-8B-Instruct</td><td><center><strong>39.47</strong></center></td><td><center>58.67</center></td><td><center><strong>67.65</strong></center></td><td><center><strong>82.77</strong></center></td><td><center>73.04</center></td><td><center>72.36</center></td><td><center>83.49</center></td><td><center>84.06</center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>39.43</center></td><td><center><strong>59.50</strong></center></td><td><center>44.45</center></td><td><center>59.76</center></td><td><center>77.20</center></td><td><center>77.87</center></td><td><center>85.80</center></td><td><center>86.05</center></td>
</tr>
<tr>
<td><em>RoLlama3-8b-Instruct-2024-10-09</em></td><td><center><em>18.89</em></center></td><td><center><em>31.79</em></center></td><td><center><em>50.84</em></center></td><td><center><em>65.18</em></center></td><td><center><em>77.60</em></center></td><td><center><em>76.86</em></center></td><td><center><em><strong>86.70</strong></em></center></td><td><center><em><strong>87.09</strong></em></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>26.05</center></td><td><center>42.77</center></td><td><center>-</center></td><td><center>-</center></td><td><center><strong>79.64</strong></center></td><td><center><strong>79.52</strong></center></td><td><center>-</center></td><td><center>-</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>Llama-3-8B-Instruct</td><td><center><strong>5.96</strong></center></td><td><center>6.16</center></td><td><center><strong>5.76</strong></center></td><td><center>158/160</center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>5.15</center></td><td><center>6.03</center></td><td><center>4.28</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3-8b-Instruct-2024-10-09</em></td><td><center><em>5.38</em></center></td><td><center><em>6.09</em></center></td><td><center><em>4.67</em></center></td><td><center><em><strong>160/160</strong></em></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>5.87</center></td><td><center><strong>6.22</strong></center></td><td><center>5.49</center></td><td><center><strong>160/160</strong></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>Llama-3-8B-Instruct</td><td><center><strong>4.62</strong></center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>3.71</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3-8b-Instruct-2024-10-09</em></td><td><center><em>3.81</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>4.40</center></td><td><center><strong>100/100</strong></center></td>
</tr>
</tbody>
</table>



## RoLlama3 Model Family

| Model              | Link  |
|--------------------|:--------:|
|RoLlama3-8b-Instruct-2024-06-28| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28) |
|*RoLlama3-8b-Instruct-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09) |
|RoLlama3-8b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-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]  -->