Upload README.md with huggingface_hub

README.md

@@ -1,760 +1,718 @@
----
-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-2024-10-09
-      results:
-        - task:
-            type: text-generation
-          dataset:
-            name: RoMT-Bench
-            type: RoMT-Bench
-          metrics:
-            - name: Score
-              type: Score
-              value: 4.43
-        - task:
-            type: text-generation
-          dataset:
-            name: RoCulturaBench
-            type: RoCulturaBench
-          metrics:
-            - name: Score
-              type: Score
-              value: 4.08
-        - task:
-            type: text-generation
-          dataset:
-            name: Romanian_Academic_Benchmarks
-            type: Romanian_Academic_Benchmarks
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 44.50
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_arc_challenge
-            type: OpenLLM-Ro/ro_arc_challenge
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 44.73
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_mmlu
-            type: OpenLLM-Ro/ro_mmlu
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 40.39
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_winogrande
-            type: OpenLLM-Ro/ro_winogrande
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 63.67
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_hellaswag
-            type: OpenLLM-Ro/ro_hellaswag
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 59.12
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_gsm8k
-            type: OpenLLM-Ro/ro_gsm8k
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 13.29
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_truthfulqa
-            type: OpenLLM-Ro/ro_truthfulqa
-          metrics:
-            - name: Average accuracy
-              type: accuracy
-              value: 45.78
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_binary
-            type: LaRoSeDa_binary
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 97.66
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_multiclass
-            type: LaRoSeDa_multiclass
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 62.41
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_binary_finetuned
-            type: LaRoSeDa_binary_finetuned
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 97.97
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_multiclass_finetuned
-            type: LaRoSeDa_multiclass_finetuned
-          metrics:
-            - name: Average macro-f1
-              type: macro-f1
-              value: 60.89
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_EN-RO
-            type: WMT_EN-RO
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 27.13
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_RO-EN
-            type: WMT_RO-EN
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 19.39
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_EN-RO_finetuned
-            type: WMT_EN-RO_finetuned
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 27.63
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_RO-EN_finetuned
-            type: WMT_RO-EN_finetuned
-          metrics:
-            - name: Average bleu
-              type: bleu
-              value: 39.75
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD
-            type: XQuAD
-          metrics:
-            - name: Average exact_match
-              type: exact_match
-              value: 45.71
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD
-            type: XQuAD
-          metrics:
-            - name: Average f1
-              type: f1
-              value: 65.08
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_finetuned
-            type: XQuAD_finetuned
-          metrics:
-            - name: Average exact_match
-              type: exact_match
-              value: 59.24
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_finetuned
-            type: XQuAD_finetuned
-          metrics:
-            - name: Average f1
-              type: f1
-              value: 74.25
-        - task:
-            type: text-generation
-          dataset:
-            name: STS
-            type: STS
-          metrics:
-            - name: Average spearman
-              type: spearman
-              value: 59.69
-        - task:
-            type: text-generation
-          dataset:
-            name: STS
-            type: STS
-          metrics:
-            - name: Average pearson
-              type: pearson
-              value: 57.16
-        - task:
-            type: text-generation
-          dataset:
-            name: STS_finetuned
-            type: STS_finetuned
-          metrics:
-            - name: Average spearman
-              type: spearman
-              value: 84.66
-        - task:
-            type: text-generation
-          dataset:
-            name: STS_finetuned
-            type: STS_finetuned
-          metrics:
-            - name: Average pearson
-              type: pearson
-              value: 85.07
-        - task:
-            type: text-generation
-          dataset:
-            name: RoMT-Bench
-            type: RoMT-Bench
-          metrics:
-            - name: First turn
-              type: Score
-              value: 4.92
-            - name: Second turn
-              type: Score
-              value: 3.94
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_arc_challenge
-            type: OpenLLM-Ro/ro_arc_challenge
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 42.67
-            - name: 1-shot 
-              type: accuracy
-              value: 44.64
-            - name: 3-shot 
-              type: accuracy
-              value: 44.90
-            - name: 5-shot 
-              type: accuracy
-              value: 45.16
-            - name: 10-shot 
-              type: accuracy
-              value: 45.67
-            - name: 25-shot 
-              type: accuracy
-              value: 45.33
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_mmlu
-            type: OpenLLM-Ro/ro_mmlu
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 39.89
-            - name: 1-shot 
-              type: accuracy
-              value: 40.08
-            - name: 3-shot 
-              type: accuracy
-              value: 40.60
-            - name: 5-shot 
-              type: accuracy
-              value: 40.99
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_winogrande
-            type: OpenLLM-Ro/ro_winogrande
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 63.06
-            - name: 1-shot 
-              type: accuracy
-              value: 62.98
-            - name: 3-shot 
-              type: accuracy
-              value: 65.19
-            - name: 5-shot 
-              type: accuracy
-              value: 63.46
-        - task:
-            type: text-generation
-          dataset:
-            name: OpenLLM-Ro/ro_hellaswag
-            type: OpenLLM-Ro/ro_hellaswag
-          metrics:
-            - name: 0-shot 
-              type: accuracy
-              value: 58.82
-            - name: 1-shot 
-              type: accuracy
-              value: 58.44
-            - name: 3-shot 
-              type: accuracy
-              value: 59.28
-            - name: 5-shot 
-              type: accuracy
-              value: 59.29
-            - name: 10-shot 
-              type: accuracy
-              value: 59.77
-        - 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: 15.01
-            - name: 5-shot 
-              type: accuracy
-              value: 18.72
-        - task:
-            type: text-generation
-          dataset:
-            name: LaRoSeDa_binary
-            type: LaRoSeDa_binary
-          metrics:
-            - name: 0-shot 
-              type: macro-f1
-              value: 98.20
-            - name: 1-shot 
-              type: macro-f1
-              value: 96.63
-            - name: 3-shot 
-              type: macro-f1
-              value: 97.67
-            - 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: 63.43
-            - name: 1-shot 
-              type: macro-f1
-              value: 53.58
-            - name: 3-shot 
-              type: macro-f1
-              value: 63.78
-            - name: 5-shot 
-              type: macro-f1
-              value: 68.85
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_EN-RO
-            type: WMT_EN-RO
-          metrics:
-            - name: 0-shot 
-              type: bleu
-              value: 20.57
-            - name: 1-shot 
-              type: bleu
-              value: 29.59
-            - name: 3-shot 
-              type: bleu
-              value: 29.50
-            - name: 5-shot 
-              type: bleu
-              value: 28.88
-        - task:
-            type: text-generation
-          dataset:
-            name: WMT_RO-EN
-            type: WMT_RO-EN
-          metrics:
-            - name: 0-shot 
-              type: bleu
-              value: 2.19
-            - name: 1-shot 
-              type: bleu
-              value: 9.97
-            - name: 3-shot 
-              type: bleu
-              value: 31.19
-            - name: 5-shot 
-              type: bleu
-              value: 34.23
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_EM
-            type: XQuAD_EM
-          metrics:
-            - name: 0-shot 
-              type: exact_match
-              value: 40.25
-            - name: 1-shot 
-              type: exact_match
-              value: 46.47
-            - name: 3-shot 
-              type: exact_match
-              value: 47.56
-            - name: 5-shot 
-              type: exact_match
-              value: 48.57
-        - task:
-            type: text-generation
-          dataset:
-            name: XQuAD_F1
-            type: XQuAD_F1
-          metrics:
-            - name: 0-shot 
-              type: f1
-              value: 62.24
-            - name: 1-shot 
-              type: f1
-              value: 65.33
-            - name: 3-shot 
-              type: f1
-              value: 65.89
-            - name: 5-shot 
-              type: f1
-              value: 66.86
-        - task:
-            type: text-generation
-          dataset:
-            name: STS_Spearman
-            type: STS_Spearman
-          metrics:
-            - name: 1-shot 
-              type: spearman
-              value: 55.44
-            - name: 3-shot 
-              type: spearman
-              value: 61.98
-            - 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: 56.18
-            - name: 3-shot 
-              type: pearson
-              value: 58.37
-            - name: 5-shot 
-              type: pearson
-              value: 56.94
-
-
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-This model points/is identical to [RoLlama2-7b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct-2024-10-09).
-
-
-
-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")
-model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct")
-
-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><strong>45.71</strong></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><em>RoLlama2-7b-Instruct-2024-10-09</em></td><td><center><em>44.50</em></center></td><td><center><em><strong>44.73</strong></em></center></td><td><center><em><strong>40.39</strong></em></center></td><td><center><em>63.67</em></center></td><td><center><em>59.12</em></center></td><td><center><em>13.29</em></center></td><td><center><em><strong>45.78</strong></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><strong>59.20</strong></center></td><td><center>15.72</center></td><td><center>39.07</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><em>RoLlama2-7b-Instruct-2024-10-09</em></td><td><center><em><strong>97.66</strong></em></center></td><td><center><em>62.41</em></center></td><td><center><em>97.97</em></center></td><td><center><em>60.89</em></center></td><td><center><em>27.13</em></center></td><td><center><em>19.39</em></center></td><td><center><em><strong>27.63</strong></em></center></td><td><center><em>39.75</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>
-</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><strong>65.50</strong></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><em>RoLlama2-7b-Instruct-2024-10-09</em></td><td><center><em><strong>45.71</strong></em></center></td><td><center><em><strong>65.08</strong></em></center></td><td><center><em>59.24</em></center></td><td><center><em>74.25</em></center></td><td><center><em>59.69</em></center></td><td><center><em>57.16</em></center></td><td><center><em><strong>84.66</strong></em></center></td><td><center><em><strong>85.07</strong></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>
-</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><em>RoLlama2-7b-Instruct-2024-10-09</em></td><td><center><em>4.43</em></center></td><td><center><em>4.92</em></center></td><td><center><em>3.94</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><strong>4.61</strong></center></td><td><center><strong>5.15</strong></center></td><td><center><strong>4.06</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><em>RoLlama2-7b-Instruct-2024-10-09</em></td><td><center><em>4.08</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><strong>4.80</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-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-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:**
-
+---
+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
+- OpenLLM-Ro/ro_sft_magpie_mt
+- OpenLLM-Ro/ro_sft_magpie_reasoning
+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: 45.7
+  - 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: 97.6
+  - 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: 46.7
+    - 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: 25.4
+  - 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: 96.3
+    - name: 3-shot
+      type: macro-f1
+      value: 97.8
+    - 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: 49.8
+    - 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: 69.7
+  - 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), [RoMagpiePro](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_mt), [RoMagpieReasoning](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_reasoning)
+
+
+### 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]  -->