| --- |
| license: cc-by-nc-4.0 |
| language: |
| - ro |
| base_model: |
| - mistralai/Mistral-7B-v0.3 |
| 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 |
| - OpenLLM-Ro/ro_sft_magpie_mt |
| - OpenLLM-Ro/ro_sft_magpie_reasoning |
| model-index: |
| - name: OpenLLM-Ro/RoMistral-7b-Instruct-2025-04-23 |
| results: |
| - task: |
| type: text-generation |
| dataset: |
| name: RoMT-Bench |
| type: RoMT-Bench |
| metrics: |
| - name: Score |
| type: Score |
| value: 6.24 |
| - task: |
| type: text-generation |
| dataset: |
| name: RoCulturaBench |
| type: RoCulturaBench |
| metrics: |
| - name: Score |
| type: Score |
| value: 4.36 |
| - task: |
| type: text-generation |
| dataset: |
| name: Romanian_Academic_Benchmarks |
| type: Romanian_Academic_Benchmarks |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 54.40 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_arc_challenge |
| type: OpenLLM-Ro/ro_arc_challenge |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 52.86 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_mmlu |
| type: OpenLLM-Ro/ro_mmlu |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 52.33 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_winogrande |
| type: OpenLLM-Ro/ro_winogrande |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 68.57 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_hellaswag |
| type: OpenLLM-Ro/ro_hellaswag |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 63.50 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_gsm8k |
| type: OpenLLM-Ro/ro_gsm8k |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 38.15 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_truthfulqa |
| type: OpenLLM-Ro/ro_truthfulqa |
| metrics: |
| - name: Average accuracy |
| type: accuracy |
| value: 51.01 |
| - task: |
| type: text-generation |
| dataset: |
| name: LaRoSeDa_binary |
| type: LaRoSeDa_binary |
| metrics: |
| - name: Average macro-f1 |
| type: macro-f1 |
| value: 97.67 |
| - task: |
| type: text-generation |
| dataset: |
| name: LaRoSeDa_multiclass |
| type: LaRoSeDa_multiclass |
| metrics: |
| - name: Average macro-f1 |
| type: macro-f1 |
| value: 61.79 |
| - task: |
| type: text-generation |
| dataset: |
| name: WMT_EN-RO |
| type: WMT_EN-RO |
| metrics: |
| - name: Average bleu |
| type: bleu |
| value: 28.69 |
| - task: |
| type: text-generation |
| dataset: |
| name: WMT_RO-EN |
| type: WMT_RO-EN |
| metrics: |
| - name: Average bleu |
| type: bleu |
| value: 19.23 |
| - task: |
| type: text-generation |
| dataset: |
| name: XQuAD |
| type: XQuAD |
| metrics: |
| - name: Average exact_match |
| type: exact_match |
| value: 49.05 |
| - task: |
| type: text-generation |
| dataset: |
| name: XQuAD |
| type: XQuAD |
| metrics: |
| - name: Average f1 |
| type: f1 |
| value: 69.11 |
| - task: |
| type: text-generation |
| dataset: |
| name: STS |
| type: STS |
| metrics: |
| - name: Average spearman |
| type: spearman |
| value: 78.67 |
| - task: |
| type: text-generation |
| dataset: |
| name: STS |
| type: STS |
| metrics: |
| - name: Average pearson |
| type: pearson |
| value: 77.08 |
| - task: |
| type: text-generation |
| dataset: |
| name: RoMT-Bench |
| type: RoMT-Bench |
| metrics: |
| - name: First turn |
| type: Score |
| value: 6.78 |
| - name: Second turn |
| type: Score |
| value: 5.70 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_arc_challenge |
| type: OpenLLM-Ro/ro_arc_challenge |
| metrics: |
| - name: 0-shot |
| type: accuracy |
| value: 50.04 |
| - name: 1-shot |
| type: accuracy |
| value: 50.99 |
| - name: 3-shot |
| type: accuracy |
| value: 53.30 |
| - name: 5-shot |
| type: accuracy |
| value: 53.73 |
| - name: 10-shot |
| type: accuracy |
| value: 54.07 |
| - name: 25-shot |
| type: accuracy |
| value: 55.01 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_mmlu |
| type: OpenLLM-Ro/ro_mmlu |
| metrics: |
| - name: 0-shot |
| type: accuracy |
| value: 51.04 |
| - name: 1-shot |
| type: accuracy |
| value: 52.53 |
| - name: 3-shot |
| type: accuracy |
| value: 53.22 |
| - name: 5-shot |
| type: accuracy |
| value: 52.52 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_winogrande |
| type: OpenLLM-Ro/ro_winogrande |
| metrics: |
| - name: 0-shot |
| type: accuracy |
| value: 66.38 |
| - name: 1-shot |
| type: accuracy |
| value: 68.90 |
| - name: 3-shot |
| type: accuracy |
| value: 68.82 |
| - name: 5-shot |
| type: accuracy |
| value: 70.17 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_hellaswag |
| type: OpenLLM-Ro/ro_hellaswag |
| metrics: |
| - name: 0-shot |
| type: accuracy |
| value: 62.61 |
| - name: 1-shot |
| type: accuracy |
| value: 63.19 |
| - name: 3-shot |
| type: accuracy |
| value: 63.46 |
| - name: 5-shot |
| type: accuracy |
| value: 63.92 |
| - name: 10-shot |
| type: accuracy |
| value: 64.34 |
| - task: |
| type: text-generation |
| dataset: |
| name: OpenLLM-Ro/ro_gsm8k |
| type: OpenLLM-Ro/ro_gsm8k |
| metrics: |
| - name: 1-shot |
| type: accuracy |
| value: 27.98 |
| - name: 3-shot |
| type: accuracy |
| value: 40.46 |
| - name: 5-shot |
| type: accuracy |
| value: 46.02 |
| - task: |
| type: text-generation |
| dataset: |
| name: LaRoSeDa_binary |
| type: LaRoSeDa_binary |
| metrics: |
| - name: 0-shot |
| type: macro-f1 |
| value: 97.87 |
| - name: 1-shot |
| type: macro-f1 |
| value: 96.73 |
| - name: 3-shot |
| type: macro-f1 |
| value: 98.20 |
| - name: 5-shot |
| type: macro-f1 |
| value: 97.87 |
| - task: |
| type: text-generation |
| dataset: |
| name: LaRoSeDa_multiclass |
| type: LaRoSeDa_multiclass |
| metrics: |
| - name: 0-shot |
| type: macro-f1 |
| value: 45.15 |
| - name: 1-shot |
| type: macro-f1 |
| value: 65.77 |
| - name: 3-shot |
| type: macro-f1 |
| value: 66.57 |
| - name: 5-shot |
| type: macro-f1 |
| value: 69.66 |
| - task: |
| type: text-generation |
| dataset: |
| name: WMT_EN-RO |
| type: WMT_EN-RO |
| metrics: |
| - name: 0-shot |
| type: bleu |
| value: 28.92 |
| - name: 1-shot |
| type: bleu |
| value: 28.42 |
| - name: 3-shot |
| type: bleu |
| value: 28.85 |
| - name: 5-shot |
| type: bleu |
| value: 28.58 |
| - task: |
| type: text-generation |
| dataset: |
| name: WMT_RO-EN |
| type: WMT_RO-EN |
| metrics: |
| - name: 0-shot |
| type: bleu |
| value: 3.56 |
| - name: 1-shot |
| type: bleu |
| value: 9.60 |
| - name: 3-shot |
| type: bleu |
| value: 29.53 |
| - name: 5-shot |
| type: bleu |
| value: 34.25 |
| - task: |
| type: text-generation |
| dataset: |
| name: XQuAD_EM |
| type: XQuAD_EM |
| metrics: |
| - name: 0-shot |
| type: exact_match |
| value: 45.21 |
| - name: 1-shot |
| type: exact_match |
| value: 49.83 |
| - name: 3-shot |
| type: exact_match |
| value: 50.34 |
| - name: 5-shot |
| type: exact_match |
| value: 50.84 |
| - task: |
| type: text-generation |
| dataset: |
| name: XQuAD_F1 |
| type: XQuAD_F1 |
| metrics: |
| - name: 0-shot |
| type: f1 |
| value: 66.40 |
| - name: 1-shot |
| type: f1 |
| value: 68.92 |
| - name: 3-shot |
| type: f1 |
| value: 70.68 |
| - name: 5-shot |
| type: f1 |
| value: 70.44 |
| - task: |
| type: text-generation |
| dataset: |
| name: STS_Spearman |
| type: STS_Spearman |
| metrics: |
| - name: 1-shot |
| type: spearman |
| value: 79.08 |
| - name: 3-shot |
| type: spearman |
| value: 78.65 |
| - name: 5-shot |
| type: spearman |
| value: 78.29 |
| - task: |
| type: text-generation |
| dataset: |
| name: STS_Pearson |
| type: STS_Pearson |
| metrics: |
| - name: 1-shot |
| type: pearson |
| value: 77.79 |
| - name: 3-shot |
| type: pearson |
| value: 76.89 |
| - name: 5-shot |
| type: pearson |
| value: 76.57 |
|
|
| --- |
| |
| # Model Card for Model ID |
|
|
| <!-- Provide a quick summary of what the model is/does. --> |
| This model points/is identical to [RoMistral-7b-Instruct-2025-04-23](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2025-04-23). |
|
|
|
|
| RoMistral 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-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:** [Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) |
| - **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), [RoMagpiePro](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_mt), [RoMagpieReasoning](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_reasoning) |
|
|
|
|
| <!-- - **Finetuned from model [optional]:** [More Information Needed] --> |
|
|
| ### 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 |
|
|
| RoMistral 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/RoMistral-7b-Instruct") |
| model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct") |
| |
| 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>Mistral-7B-Instruct-v0.2</td><td><center>47.40</center></td><td><center>46.29</center></td><td><center>47.00</center></td><td><center>58.78</center></td><td><center>54.27</center></td><td><center>13.47</center></td><td><center><strong>64.59</strong></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-05-17</td><td><center>52.54</center></td><td><center>50.41</center></td><td><center>51.61</center></td><td><center>66.48</center></td><td><center>60.27</center></td><td><center>34.19</center></td><td><center>52.30</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-10-09</td><td><center>52.91</center></td><td><center>52.27</center></td><td><center>49.33</center></td><td><center><strong>70.03</strong></center></td><td><center>62.88</center></td><td><center>32.42</center></td><td><center>50.51</center></td> |
| </tr> |
| <tr> |
| <td><em>RoMistral-7b-Instruct-2025-04-23</em></td><td><center><em>54.40</em></center></td><td><center><em>52.86</em></center></td><td><center><em>52.33</em></center></td><td><center><em>68.57</em></center></td><td><center><em>63.50</em></center></td><td><center><em>38.15</em></center></td><td><center><em>51.01</em></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2024-10-09</td><td><center>51.95</center></td><td><center>50.73</center></td><td><center>47.88</center></td><td><center>68.41</center></td><td><center>62.27</center></td><td><center>32.27</center></td><td><center>50.12</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2025-04-23</td><td><center><strong>56.62</strong></center></td><td><center><strong>55.51</strong></center></td><td><center><strong>52.61</strong></center></td><td><center>68.04</center></td><td><center><strong>64.97</strong></center></td><td><center><strong>41.07</strong></center></td><td><center>57.55</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>Mistral-7B-Instruct-v0.2</td><td><center>96.97</center></td><td><center>56.66</center></td><td><center>98.83</center></td><td><center>87.32</center></td><td><center>18.60</center></td><td><center><strong>33.99</strong></center></td><td><center>26.19</center></td><td><center>39.88</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-05-17</td><td><center>97.36</center></td><td><center>67.55</center></td><td><center>98.80</center></td><td><center><strong>88.28</strong></center></td><td><center>27.93</center></td><td><center>13.21</center></td><td><center><strong>28.72</strong></center></td><td><center><strong>40.86</strong></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-10-09</td><td><center>95.56</center></td><td><center><strong>67.83</strong></center></td><td><center><strong>99.00</strong></center></td><td><center>87.57</center></td><td><center>28.28</center></td><td><center>6.10</center></td><td><center>27.70</center></td><td><center>40.36</center></td> |
| </tr> |
| <tr> |
| <td><em>RoMistral-7b-Instruct-2025-04-23</em></td><td><center><em>97.67</em></center></td><td><center><em>61.79</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>28.69</strong></em></center></td><td><center><em>19.23</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2024-10-09</td><td><center>82.13</center></td><td><center>65.24</center></td><td><center>-</center></td><td><center>-</center></td><td><center>26.25</center></td><td><center>6.09</center></td><td><center>-</center></td><td><center>-</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2025-04-23</td><td><center><strong>97.94</strong></center></td><td><center>66.13</center></td><td><center>-</center></td><td><center>-</center></td><td><center>27.24</center></td><td><center>18.41</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>Mistral-7B-Instruct-v0.2</td><td><center>27.92</center></td><td><center>50.71</center></td><td><center><strong>65.46</strong></center></td><td><center><strong>79.73</strong></center></td><td><center>62.62</center></td><td><center>60.86</center></td><td><center>84.92</center></td><td><center>85.44</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-05-17</td><td><center>43.66</center></td><td><center>63.70</center></td><td><center>55.04</center></td><td><center>72.31</center></td><td><center>77.43</center></td><td><center><strong>78.43</strong></center></td><td><center>87.25</center></td><td><center>87.79</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-10-09</td><td><center>41.09</center></td><td><center>63.21</center></td><td><center>47.56</center></td><td><center>62.69</center></td><td><center>78.47</center></td><td><center>77.24</center></td><td><center><strong>87.28</strong></center></td><td><center><strong>87.88</strong></center></td> |
| </tr> |
| <tr> |
| <td><em>RoMistral-7b-Instruct-2025-04-23</em></td><td><center><em><strong>49.05</strong></em></center></td><td><center><em><strong>69.11</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>78.67</strong></em></center></td><td><center><em>77.08</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2024-10-09</td><td><center>23.40</center></td><td><center>45.80</center></td><td><center>-</center></td><td><center>-</center></td><td><center>77.33</center></td><td><center>76.60</center></td><td><center>-</center></td><td><center>-</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2025-04-23</td><td><center>40.86</center></td><td><center>62.24</center></td><td><center>-</center></td><td><center>-</center></td><td><center>77.89</center></td><td><center>76.40</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>Mistral-7B-Instruct-v0.2</td><td><center>5.03</center></td><td><center>5.05</center></td><td><center>5.00</center></td><td><center>154/160</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-05-17</td><td><center>4.99</center></td><td><center>5.46</center></td><td><center>4.53</center></td><td><center><strong>160/160</strong></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-10-09</td><td><center>5.29</center></td><td><center>5.86</center></td><td><center>4.72</center></td><td><center><strong>160/160</strong></center></td> |
| </tr> |
| <tr> |
| <td><em>RoMistral-7b-Instruct-2025-04-23</em></td><td><center><em>6.24</em></center></td><td><center><em>6.78</em></center></td><td><center><em>5.70</em></center></td><td><center><em><strong>160/160</strong></em></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2024-10-09</td><td><center>5.88</center></td><td><center>6.44</center></td><td><center>5.33</center></td><td><center><strong>160/160</strong></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2025-04-23</td><td><center><strong>6.61</strong></center></td><td><center><strong>6.86</strong></center></td><td><center><strong>6.35</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>Mistral-7B-Instruct-v0.2</td><td><center>3.68</center></td><td><center>97/100</center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-05-17</td><td><center>3.38</center></td><td><center><strong>100/100</strong></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-2024-10-09</td><td><center>3.99</center></td><td><center><strong>100/100</strong></center></td> |
| </tr> |
| <tr> |
| <td><em>RoMistral-7b-Instruct-2025-04-23</em></td><td><center><em>4.36</em></center></td><td><center><em><strong>100/100</strong></em></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2024-10-09</td><td><center>4.72</center></td><td><center><strong>100/100</strong></center></td> |
| </tr> |
| <tr> |
| <td>RoMistral-7b-Instruct-DPO-2025-04-23</td><td><center><strong>4.93</strong></center></td><td><center><strong>100/100</strong></center></td> |
| </tr> |
| </tbody> |
| </table> |
|
|
|
|
|
|
|
|
| ## RoMistral Model Family |
|
|
| | Model | Link | |
| |--------------------|:--------:| |
| |RoMistral-7b-Instruct-2024-05-17| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17) | |
| |RoMistral-7b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09) | |
| |*RoMistral-7b-Instruct-2025-04-23*| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2025-04-23) | |
| |RoMistral-7b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2024-10-09) | |
| |RoMistral-7b-Instruct-DPO-2025-04-23| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2025-04-23) | |
|
|
|
|
|
|
| ## Citation |
|
|
| ``` |
| @inproceedings{masala-etal-2024-vorbesti, |
| title = "``Vorbe\c{s}ti Rom{\^a}ne\c{s}te?'' A Recipe to Train Powerful {R}omanian {LLM}s with {E}nglish Instructions", |
| author = "Masala, Mihai and Ilie-Ablachim, Denis and Dima, Alexandru and Corlatescu, Dragos Georgian and Zavelca, Miruna-Andreea and Olaru, Ovio and Terian, Simina-Maria and Terian, Andrei and Leordeanu, Marius and Velicu, Horia and Popescu, Marius and Dascalu, Mihai and Rebedea, Traian", |
| editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", |
| booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024", |
| month = nov, |
| year = "2024", |
| address = "Miami, Florida, USA", |
| publisher = "Association for Computational Linguistics", |
| url = "https://aclanthology.org/2024.findings-emnlp.681/", |
| doi = "10.18653/v1/2024.findings-emnlp.681", |
| pages = "11632--11647" |
| } |
| ``` |
| <!-- **APA:** |
|
|
| [More Information Needed] --> |
