---
license: cc-by-nc-4.0
language:
- ro
base_model:
- OpenLLM-Ro/RoLlama3-8b-Instruct-2025-04-23
datasets:
- OpenLLM-Ro/ro_dpo_helpsteer
- OpenLLM-Ro/ro_dpo_ultrafeedback
- OpenLLM-Ro/ro_dpo_magpie
- OpenLLM-Ro/ro_dpo_argilla_magpie
- OpenLLM-Ro/ro_dpo_helpsteer2
model-index:
    - name: OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2025-04-23
      results:
        - task:
            type: text-generation
          dataset:
            name: RoMT-Bench
            type: RoMT-Bench
          metrics:
            - name: Score
              type: Score
              value: 6.67
        - 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: 55.86
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_arc_challenge
            type: OpenLLM-Ro/ro_arc_challenge
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 52.26
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_mmlu
            type: OpenLLM-Ro/ro_mmlu
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 55.35
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_winogrande
            type: OpenLLM-Ro/ro_winogrande
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 66.62
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_hellaswag
            type: OpenLLM-Ro/ro_hellaswag
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 59.93
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_gsm8k
            type: OpenLLM-Ro/ro_gsm8k
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 43.95
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_truthfulqa
            type: OpenLLM-Ro/ro_truthfulqa
          metrics:
            - name: Average accuracy
              type: accuracy
              value: 57.06
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_binary
            type: LaRoSeDa_binary
          metrics:
            - name: Average macro-f1
              type: macro-f1
              value: 97.60
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_multiclass
            type: LaRoSeDa_multiclass
          metrics:
            - name: Average macro-f1
              type: macro-f1
              value: 62.16
        - task:
            type: text-generation
          dataset:
            name: WMT_EN-RO
            type: WMT_EN-RO
          metrics:
            - name: Average bleu
              type: bleu
              value: 18.14
        - task:
            type: text-generation
          dataset:
            name: WMT_RO-EN
            type: WMT_RO-EN
          metrics:
            - name: Average bleu
              type: bleu
              value: 14.13
        - task:
            type: text-generation
          dataset:
            name: XQuAD
            type: XQuAD
          metrics:
            - name: Average exact_match
              type: exact_match
              value: 30.65
        - task:
            type: text-generation
          dataset:
            name: XQuAD
            type: XQuAD
          metrics:
            - name: Average f1
              type: f1
              value: 46.29
        - task:
            type: text-generation
          dataset:
            name: STS
            type: STS
          metrics:
            - name: Average spearman
              type: spearman
              value: 67.62
        - task:
            type: text-generation
          dataset:
            name: STS
            type: STS
          metrics:
            - name: Average pearson
              type: pearson
              value: 67.82
        - task:
            type: text-generation
          dataset:
            name: RoMT-Bench
            type: RoMT-Bench
          metrics:
            - name: First turn
              type: Score
              value: 6.81
            - name: Second turn
              type: Score
              value: 6.54
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_arc_challenge
            type: OpenLLM-Ro/ro_arc_challenge
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 48.76
            - name: 1-shot 
              type: accuracy
              value: 49.70
            - name: 3-shot 
              type: accuracy
              value: 52.70
            - name: 5-shot 
              type: accuracy
              value: 54.07
            - name: 10-shot 
              type: accuracy
              value: 53.90
            - name: 25-shot 
              type: accuracy
              value: 54.41
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_mmlu
            type: OpenLLM-Ro/ro_mmlu
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 55.78
            - name: 1-shot 
              type: accuracy
              value: 55.09
            - name: 3-shot 
              type: accuracy
              value: 55.39
            - name: 5-shot 
              type: accuracy
              value: 55.15
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_winogrande
            type: OpenLLM-Ro/ro_winogrande
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 65.19
            - name: 1-shot 
              type: accuracy
              value: 64.25
            - name: 3-shot 
              type: accuracy
              value: 68.59
            - name: 5-shot 
              type: accuracy
              value: 68.43
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_hellaswag
            type: OpenLLM-Ro/ro_hellaswag
          metrics:
            - name: 0-shot 
              type: accuracy
              value: 60.31
            - name: 1-shot 
              type: accuracy
              value: 59.88
            - name: 3-shot 
              type: accuracy
              value: 59.17
            - name: 5-shot 
              type: accuracy
              value: 59.89
            - name: 10-shot 
              type: accuracy
              value: 60.40
        - task:
            type: text-generation
          dataset:
            name: OpenLLM-Ro/ro_gsm8k
            type: OpenLLM-Ro/ro_gsm8k
          metrics:
            - name: 1-shot 
              type: accuracy
              value: 32.37
            - name: 3-shot 
              type: accuracy
              value: 46.70
            - name: 5-shot 
              type: accuracy
              value: 52.77
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_binary
            type: LaRoSeDa_binary
          metrics:
            - name: 0-shot 
              type: macro-f1
              value: 95.79
            - name: 1-shot 
              type: macro-f1
              value: 97.87
            - name: 3-shot 
              type: macro-f1
              value: 98.30
            - name: 5-shot 
              type: macro-f1
              value: 98.43
        - task:
            type: text-generation
          dataset:
            name: LaRoSeDa_multiclass
            type: LaRoSeDa_multiclass
          metrics:
            - name: 0-shot 
              type: macro-f1
              value: 64.86
            - name: 1-shot 
              type: macro-f1
              value: 64.46
            - name: 3-shot 
              type: macro-f1
              value: 58.36
            - name: 5-shot 
              type: macro-f1
              value: 60.97
        - task:
            type: text-generation
          dataset:
            name: WMT_EN-RO
            type: WMT_EN-RO
          metrics:
            - name: 0-shot 
              type: bleu
              value: 5.57
            - name: 1-shot 
              type: bleu
              value: 26.05
            - name: 3-shot 
              type: bleu
              value: 24.71
            - name: 5-shot 
              type: bleu
              value: 16.22
        - task:
            type: text-generation
          dataset:
            name: WMT_RO-EN
            type: WMT_RO-EN
          metrics:
            - name: 0-shot 
              type: bleu
              value: 3.01
            - name: 1-shot 
              type: bleu
              value: 22.63
            - name: 3-shot 
              type: bleu
              value: 19.43
            - name: 5-shot 
              type: bleu
              value: 11.47
        - task:
            type: text-generation
          dataset:
            name: XQuAD_EM
            type: XQuAD_EM
          metrics:
            - name: 0-shot 
              type: exact_match
              value: 16.55
            - name: 1-shot 
              type: exact_match
              value: 31.76
            - name: 3-shot 
              type: exact_match
              value: 35.97
            - name: 5-shot 
              type: exact_match
              value: 38.32
        - task:
            type: text-generation
          dataset:
            name: XQuAD_F1
            type: XQuAD_F1
          metrics:
            - name: 0-shot 
              type: f1
              value: 33.31
            - name: 1-shot 
              type: f1
              value: 46.85
            - name: 3-shot 
              type: f1
              value: 50.73
            - name: 5-shot 
              type: f1
              value: 54.29
        - task:
            type: text-generation
          dataset:
            name: STS_Spearman
            type: STS_Spearman
          metrics:
            - name: 1-shot 
              type: spearman
              value: 66.56
            - name: 3-shot 
              type: spearman
              value: 58.64
            - name: 5-shot 
              type: spearman
              value: 77.66
        - task:
            type: text-generation
          dataset:
            name: STS_Pearson
            type: STS_Pearson
          metrics:
            - name: 1-shot 
              type: pearson
              value: 70.09
            - name: 3-shot 
              type: pearson
              value: 56.39
            - name: 5-shot 
              type: pearson
              value: 76.97

---

# Model Card for Model ID

*Built with Meta Llama 3*

This model points/is identical to [RoLlama3-8b-Instruct-DPO-2025-04-23](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2025-04-23).

RoLlama3 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **human aligned 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 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:** [RoLlama3-8b-Instruct-2025-04-23](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2025-04-23)
- **Trained using:** [RoHelpSteer](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_helpsteer), [RoUltraFeedback](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_ultrafeedback), [RoMagpieDPO](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_magpie), [RoArgillaMagpie](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_argilla_magpie), [RoHelpSteer2](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_helpsteer2)


### 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-DPO")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama3-8b-Instruct-DPO")

instruction = "Care este cel mai înalt vârf muntos din România?"
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)

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>43.87</center></td><td><center>51.59</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>RoLlama3-8b-Instruct-2024-10-09</td><td><center>52.21</center></td><td><center>47.94</center></td><td><center>53.50</center></td><td><center>66.06</center></td><td><center>59.72</center></td><td><center>40.16</center></td><td><center>45.90</center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2025-04-23</td><td><center>54.66</center></td><td><center>50.31</center></td><td><center><strong>55.91</strong></center></td><td><center>67.01</center></td><td><center><strong>61.73</strong></center></td><td><center><strong>47.41</strong></center></td><td><center>45.61</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>
<tr>
<td><em>RoLlama3-8b-Instruct-DPO-2025-04-23</em></td><td><center><em><strong>55.86</strong></em></center></td><td><center><em><strong>52.26</strong></em></center></td><td><center><em>55.35</em></center></td><td><center><em>66.62</em></center></td><td><center><em>59.93</em></center></td><td><center><em>43.95</em></center></td><td><center><em><strong>57.06</strong></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>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>97.52</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>RoLlama3-8b-Instruct-2024-10-09</td><td><center>95.58</center></td><td><center>61.20</center></td><td><center>96.46</center></td><td><center><strong>87.26</strong></center></td><td><center>22.92</center></td><td><center>24.28</center></td><td><center>27.31</center></td><td><center><strong>40.52</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2025-04-23</td><td><center>96.21</center></td><td><center>59.15</center></td><td><center>-</center></td><td><center>-</center></td><td><center>23.32</center></td><td><center>22.50</center></td><td><center>-</center></td><td><center>-</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>
<tr>
<td><em>RoLlama3-8b-Instruct-DPO-2025-04-23</em></td><td><center><em><strong>97.60</strong></em></center></td><td><center><em>62.16</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>18.14</em></center></td><td><center><em>14.13</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>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>RoLlama3-8b-Instruct-2024-10-09</td><td><center>18.89</center></td><td><center>31.79</center></td><td><center>50.84</center></td><td><center>65.18</center></td><td><center>77.60</center></td><td><center>76.86</center></td><td><center><strong>86.70</strong></center></td><td><center><strong>87.09</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2025-04-23</td><td><center>11.01</center></td><td><center>23.55</center></td><td><center>-</center></td><td><center>-</center></td><td><center>76.78</center></td><td><center>74.36</center></td><td><center>-</center></td><td><center>-</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>
<tr>
<td><em>RoLlama3-8b-Instruct-DPO-2025-04-23</em></td><td><center><em>30.65</em></center></td><td><center><em>46.29</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>67.62</em></center></td><td><center><em>67.82</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
</tr>
</tbody>
</table>


## Romanian 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>5.96</center></td><td><center>6.16</center></td><td><center>5.76</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>RoLlama3-8b-Instruct-2024-10-09</td><td><center>5.38</center></td><td><center>6.09</center></td><td><center>4.67</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2025-04-23</td><td><center>6.39</center></td><td><center><strong>7.12</strong></center></td><td><center>5.66</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-DPO-2024-10-09</td><td><center>5.87</center></td><td><center>6.22</center></td><td><center>5.49</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3-8b-Instruct-DPO-2025-04-23</em></td><td><center><em><strong>6.67</strong></em></center></td><td><center><em>6.81</em></center></td><td><center><em><strong>6.54</strong></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>Llama-3-8B-Instruct</td><td><center>4.62</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>RoLlama3-8b-Instruct-2024-10-09</td><td><center>3.81</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td>RoLlama3-8b-Instruct-2025-04-23</td><td><center>4.05</center></td><td><center><strong>100/100</strong></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>
<tr>
<td><em>RoLlama3-8b-Instruct-DPO-2025-04-23</em></td><td><center><em><strong>4.83</strong></em></center></td><td><center><em><strong>100/100</strong></em></center></td>
</tr>
</tbody>
</table>



## RoLlama3 Model Family

| Model              | Link  |
|--------------------|:--------:|
|RoLlama3-8b-Base-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlam32-8b-Base-2024-05-14)    |
|RoLlama3-8b-Instruct-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-05-14)    |
|RoLlama3-8b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09) |
|RoLlama3-8b-Instruct-2025-04-23| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2025-04-23) |
|RoLlama3-8b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2024-10-09) |
|*RoLlama3-8b-Instruct-DPO-2025-04-23*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2025-04-23) |



## 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]  -->