OpenLLM-Ro
/

RoLlama2-7b-Instruct-2025-04-23

+---
+license: cc-by-nc-4.0
+language:
+- ro
+base_model:
+- OpenLLM-Ro/RoLlama2-7b-Base
+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/RoLlama2-7b-Instruct-2025-04-23
+      results:
+        - task:
+            type: text-generation
+          dataset:
+            name: RoMT-Bench
+            type: RoMT-Bench
+          metrics:
+            - name: Score
+              type: Score
+              value: 4.97
+        - task:
+            type: text-generation
+          dataset:
+            name: RoCulturaBench
+            type: RoCulturaBench
+          metrics:
+            - name: Score
+              type: Score
+              value: 4.56
+        - task:
+            type: text-generation
+          dataset:
+            name: Romanian_Academic_Benchmarks
+            type: Romanian_Academic_Benchmarks
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 45.51
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_arc_challenge
+            type: OpenLLM-Ro/ro_arc_challenge
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 45.70
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_mmlu
+            type: OpenLLM-Ro/ro_mmlu
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 40.36
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_winogrande
+            type: OpenLLM-Ro/ro_winogrande
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 63.26
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_hellaswag
+            type: OpenLLM-Ro/ro_hellaswag
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 60.25
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_gsm8k
+            type: OpenLLM-Ro/ro_gsm8k
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 18.02
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_truthfulqa
+            type: OpenLLM-Ro/ro_truthfulqa
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 45.48
+        - 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: 60.22
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_EN-RO
+            type: WMT_EN-RO
+          metrics:
+            - name: Average bleu
+              type: bleu
+              value: 27.21
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_RO-EN
+            type: WMT_RO-EN
+          metrics:
+            - name: Average bleu
+              type: bleu
+              value: 22.15
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD
+            type: XQuAD
+          metrics:
+            - name: Average exact_match
+              type: exact_match
+              value: 47.39
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD
+            type: XQuAD
+          metrics:
+            - name: Average f1
+              type: f1
+              value: 65.77
+        - task:
+            type: text-generation
+          dataset:
+            name: STS
+            type: STS
+          metrics:
+            - name: Average spearman
+              type: spearman
+              value: 59.05
+        - task:
+            type: text-generation
+          dataset:
+            name: STS
+            type: STS
+          metrics:
+            - name: Average pearson
+              type: pearson
+              value: 56.45
+        - task:
+            type: text-generation
+          dataset:
+            name: RoMT-Bench
+            type: RoMT-Bench
+          metrics:
+            - name: First turn
+              type: Score
+              value: 5.56
+            - name: Second turn
+              type: Score
+              value: 4.39
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_arc_challenge
+            type: OpenLLM-Ro/ro_arc_challenge
+          metrics:
+            - name: 0-shot
+              type: accuracy
+              value: 43.02
+            - name: 1-shot
+              type: accuracy
+              value: 45.84
+            - name: 3-shot
+              type: accuracy
+              value: 45.24
+            - name: 5-shot
+              type: accuracy
+              value: 46.19
+            - name: 10-shot
+              type: accuracy
+              value: 46.70
+            - name: 25-shot
+              type: accuracy
+              value: 47.22
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_mmlu
+            type: OpenLLM-Ro/ro_mmlu
+          metrics:
+            - name: 0-shot
+              type: accuracy
+              value: 38.64
+            - name: 1-shot
+              type: accuracy
+              value: 40.77
+            - name: 3-shot
+              type: accuracy
+              value: 41.19
+            - name: 5-shot
+              type: accuracy
+              value: 40.86
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_winogrande
+            type: OpenLLM-Ro/ro_winogrande
+          metrics:
+            - name: 0-shot
+              type: accuracy
+              value: 63.61
+            - name: 1-shot
+              type: accuracy
+              value: 62.75
+            - name: 3-shot
+              type: accuracy
+              value: 63.46
+            - name: 5-shot
+              type: accuracy
+              value: 63.22
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_hellaswag
+            type: OpenLLM-Ro/ro_hellaswag
+          metrics:
+            - name: 0-shot
+              type: accuracy
+              value: 59.79
+            - name: 1-shot
+              type: accuracy
+              value: 59.62
+            - name: 3-shot
+              type: accuracy
+              value: 60.12
+            - name: 5-shot
+              type: accuracy
+              value: 60.71
+            - name: 10-shot
+              type: accuracy
+              value: 61.01
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_gsm8k
+            type: OpenLLM-Ro/ro_gsm8k
+          metrics:
+            - name: 1-shot
+              type: accuracy
+              value: 6.14
+            - name: 3-shot
+              type: accuracy
+              value: 22.52
+            - name: 5-shot
+              type: accuracy
+              value: 25.40
+        - task:
+            type: text-generation
+          dataset:
+            name: LaRoSeDa_binary
+            type: LaRoSeDa_binary
+          metrics:
+            - name: 0-shot
+              type: macro-f1
+              value: 98.17
+            - name: 1-shot
+              type: macro-f1
+              value: 96.30
+            - name: 3-shot
+              type: macro-f1
+              value: 97.80
+            - name: 5-shot
+              type: macro-f1
+              value: 98.13
+        - task:
+            type: text-generation
+          dataset:
+            name: LaRoSeDa_multiclass
+            type: LaRoSeDa_multiclass
+          metrics:
+            - name: 0-shot
+              type: macro-f1
+              value: 49.80
+            - name: 1-shot
+              type: macro-f1
+              value: 56.03
+            - name: 3-shot
+              type: macro-f1
+              value: 65.33
+            - name: 5-shot
+              type: macro-f1
+              value: 69.70
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_EN-RO
+            type: WMT_EN-RO
+          metrics:
+            - name: 0-shot
+              type: bleu
+              value: 19.34
+            - name: 1-shot
+              type: bleu
+              value: 29.89
+            - name: 3-shot
+              type: bleu
+              value: 29.99
+            - name: 5-shot
+              type: bleu
+              value: 29.62
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_RO-EN
+            type: WMT_RO-EN
+          metrics:
+            - name: 0-shot
+              type: bleu
+              value: 2.29
+            - name: 1-shot
+              type: bleu
+              value: 14.74
+            - name: 3-shot
+              type: bleu
+              value: 34.82
+            - name: 5-shot
+              type: bleu
+              value: 36.75
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD_EM
+            type: XQuAD_EM
+          metrics:
+            - name: 0-shot
+              type: exact_match
+              value: 42.86
+            - name: 1-shot
+              type: exact_match
+              value: 47.82
+            - name: 3-shot
+              type: exact_match
+              value: 48.32
+            - name: 5-shot
+              type: exact_match
+              value: 50.59
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD_F1
+            type: XQuAD_F1
+          metrics:
+            - name: 0-shot
+              type: f1
+              value: 63.66
+            - name: 1-shot
+              type: f1
+              value: 65.27
+            - name: 3-shot
+              type: f1
+              value: 66.04
+            - name: 5-shot
+              type: f1
+              value: 68.12
+        - task:
+            type: text-generation
+          dataset:
+            name: STS_Spearman
+            type: STS_Spearman
+          metrics:
+            - name: 1-shot
+              type: spearman
+              value: 54.51
+            - name: 3-shot
+              type: spearman
+              value: 60.98
+            - name: 5-shot
+              type: spearman
+              value: 61.65
+        - task:
+            type: text-generation
+          dataset:
+            name: STS_Pearson
+            type: STS_Pearson
+          metrics:
+            - name: 1-shot
+              type: pearson
+              value: 54.35
+            - name: 3-shot
+              type: pearson
+              value: 57.88
+            - name: 5-shot
+              type: pearson
+              value: 57.13
+---
+# Model Card for Model ID
+<!-- Provide a quick summary of what the model is/does. -->
+RoLlama2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **instruct 7B 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:** [RoLlama2-7b-Base](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base)
+- **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
+RoLlama2 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/RoLlama2-7b-Instruct-2025-04-23")
+model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23")
+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-2-7b-chat</td><td><center>36.84</center></td><td><center>37.03</center></td><td><center>33.80</center></td><td><center>55.87</center></td><td><center>45.36</center></td><td><center>4.90</center></td><td><center>44.09</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>45.71</center></td><td><center>43.66</center></td><td><center>39.70</center></td><td><center><strong>70.34</strong></center></td><td><center>57.36</center></td><td><center><strong>18.78</strong></center></td><td><center>44.44</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>44.50</center></td><td><center>44.73</center></td><td><center>40.39</center></td><td><center>63.67</center></td><td><center>59.12</center></td><td><center>13.29</center></td><td><center>45.78</center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>45.51</em></center></td><td><center><em>45.70</em></center></td><td><center><em>40.36</em></center></td><td><center><em>63.26</em></center></td><td><center><em>60.25</em></center></td><td><center><em>18.02</em></center></td><td><center><em>45.48</em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>43.20</center></td><td><center>44.24</center></td><td><center>38.39</center></td><td><center>62.57</center></td><td><center>59.20</center></td><td><center>15.72</center></td><td><center>39.07</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>46.77</strong></center></td><td><center><strong>48.16</strong></center></td><td><center><strong>41.38</strong></center></td><td><center>64.15</center></td><td><center><strong>61.37</strong></center></td><td><center>18.35</center></td><td><center><strong>47.20</strong></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-2-7b-chat</td><td><center>87.78</center></td><td><center>52.81</center></td><td><center>97.27</center></td><td><center>82.02</center></td><td><center>15.55</center></td><td><center><strong>28.53</strong></center></td><td><center>19.99</center></td><td><center>31.48</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>97.48</center></td><td><center><strong>65.26</strong></center></td><td><center><strong>98.83</strong></center></td><td><center><strong>87.28</strong></center></td><td><center><strong>27.38</strong></center></td><td><center>10.32</center></td><td><center>27.59</center></td><td><center><strong>40.13</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>97.66</center></td><td><center>62.41</center></td><td><center>97.97</center></td><td><center>60.89</center></td><td><center>27.13</center></td><td><center>19.39</center></td><td><center><strong>27.63</strong></center></td><td><center>39.75</center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>97.60</em></center></td><td><center><em>60.22</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>27.21</em></center></td><td><center><em>22.15</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>97.31</center></td><td><center>60.56</center></td><td><center>-</center></td><td><center>-</center></td><td><center>26.56</center></td><td><center>21.68</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>97.77</strong></center></td><td><center>65.21</center></td><td><center>-</center></td><td><center>-</center></td><td><center>25.48</center></td><td><center>22.75</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-2-7b-chat</td><td><center>32.35</center></td><td><center>54.00</center></td><td><center><strong>60.34</strong></center></td><td><center><strong>75.98</strong></center></td><td><center>32.56</center></td><td><center>31.99</center></td><td><center>74.08</center></td><td><center>72.64</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>44.52</center></td><td><center>64.75</center></td><td><center>54.96</center></td><td><center>70.20</center></td><td><center>65.50</center></td><td><center><strong>67.79</strong></center></td><td><center>84.44</center></td><td><center>84.76</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>45.71</center></td><td><center>65.08</center></td><td><center>59.24</center></td><td><center>74.25</center></td><td><center>59.69</center></td><td><center>57.16</center></td><td><center><strong>84.66</strong></center></td><td><center><strong>85.07</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em><strong>47.39</strong></em></center></td><td><center><em><strong>65.77</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>59.05</em></center></td><td><center><em>56.45</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>35.78</center></td><td><center>59.31</center></td><td><center>-</center></td><td><center>-</center></td><td><center>61.22</center></td><td><center>58.41</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center>38.28</center></td><td><center>60.88</center></td><td><center>-</center></td><td><center>-</center></td><td><center><strong>66.76</strong></center></td><td><center>64.72</center></td><td><center>-</center></td><td><center>-</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-2-7b-chat</td><td><center>1.08</center></td><td><center>1.44</center></td><td><center>0.73</center></td><td><center>45/160</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>3.86</center></td><td><center>4.67</center></td><td><center>3.04</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>4.43</center></td><td><center>4.92</center></td><td><center>3.94</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>4.97</em></center></td><td><center><em>5.56</em></center></td><td><center><em>4.39</em></center></td><td><center><em><strong>160/160</strong></em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>4.61</center></td><td><center>5.15</center></td><td><center>4.06</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>5.55</strong></center></td><td><center><strong>5.84</strong></center></td><td><center><strong>5.26</strong></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-2-7b-chat</td><td><center>1.21</center></td><td><center>33/100</center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-05-14</td><td><center>3.77</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>4.08</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td><em>RoLlama2-7b-Instruct-2025-04-23</em></td><td><center><em>4.56</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2024-10-09</td><td><center>4.80</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td>RoLlama2-7b-Instruct-DPO-2025-04-23</td><td><center><strong>5.24</strong></center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+</tbody>
+</table>
+## RoLlama2 Model Family
+| Model              | Link  |
+|--------------------|:--------:|
+|RoLlama2-7b-Base-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14)    |
+|RoLlama2-7b-Instruct-2024-05-14 | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-05-14)    |
+|RoLlama2-7b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-10-09) |
+|*RoLlama2-7b-Instruct-2025-04-23*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2025-04-23) |
+|RoLlama2-7b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-DPO-2024-10-09) |
+|RoLlama2-7b-Instruct-DPO-2025-04-23| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-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]  -->