Update README.md

README.md

@@ -1,3 +1,745 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+language:
+- ro
+base_model:
+- OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09
+datasets:
+- OpenLLM-Ro/ro_dpo_helpsteer
+model-index:
+- name: OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2024-10-09
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - name: Score
+      type: Score
+      value: 5.88
+  - task:
+      type: text-generation
+    dataset:
+      name: RoCulturaBench
+      type: RoCulturaBench
+    metrics:
+    - name: Score
+      type: Score
+      value: 4.72
+  - task:
+      type: text-generation
+    dataset:
+      name: Romanian_Academic_Benchmarks
+      type: Romanian_Academic_Benchmarks
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 51.95
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 50.73
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 47.88
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 68.41
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 62.27
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 32.27
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_truthfulqa
+      type: OpenLLM-Ro/ro_truthfulqa
+    metrics:
+    - name: Average accuracy
+      type: accuracy
+      value: 50.12
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 82.13
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 65.24
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary_finetuned
+      type: LaRoSeDa_binary_finetuned
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass_finetuned
+      type: LaRoSeDa_multiclass_finetuned
+    metrics:
+    - name: Average macro-f1
+      type: macro-f1
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 26.25
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 6.09
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO_finetuned
+      type: WMT_EN-RO_finetuned
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN_finetuned
+      type: WMT_RO-EN_finetuned
+    metrics:
+    - name: Average bleu
+      type: bleu
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 23.4
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 45.8
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - name: Average exact_match
+      type: exact_match
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - name: Average f1
+      type: f1
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 77.33
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 76.6
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - name: Average spearman
+      type: spearman
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - name: Average pearson
+      type: pearson
+      value: 0
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - name: First turn
+      type: Score
+      value: 6.44
+    - name: Second turn
+      type: Score
+      value: 5.33
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 51.67
+    - name: 1-shot
+      type: accuracy
+      value: 45.59
+    - name: 3-shot
+      type: accuracy
+      value: 48.24
+    - name: 5-shot
+      type: accuracy
+      value: 50.21
+    - name: 10-shot
+      type: accuracy
+      value: 54.07
+    - name: 25-shot
+      type: accuracy
+      value: 54.58
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 40.86
+    - name: 1-shot
+      type: accuracy
+      value: 48.67
+    - name: 3-shot
+      type: accuracy
+      value: 51.26
+    - name: 5-shot
+      type: accuracy
+      value: 50.75
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 64.8
+    - name: 1-shot
+      type: accuracy
+      value: 68.19
+    - name: 3-shot
+      type: accuracy
+      value: 70.09
+    - name: 5-shot
+      type: accuracy
+      value: 70.56
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 61.96
+    - name: 1-shot
+      type: accuracy
+      value: 60.88
+    - name: 3-shot
+      type: accuracy
+      value: 61.86
+    - name: 5-shot
+      type: accuracy
+      value: 62.73
+    - name: 10-shot
+      type: accuracy
+      value: 63.93
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - name: 0-shot
+      type: accuracy
+      value: 23.28
+    - name: 1-shot
+      type: accuracy
+      value: 34.95
+    - name: 3-shot
+      type: accuracy
+      value: 38.59
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 34.36
+    - name: 1-shot
+      type: macro-f1
+      value: 97.87
+    - name: 3-shot
+      type: macro-f1
+      value: 98.4
+    - name: 5-shot
+      type: macro-f1
+      value: 97.9
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - name: 0-shot
+      type: macro-f1
+      value: 66.17
+    - name: 1-shot
+      type: macro-f1
+      value: 65.93
+    - name: 3-shot
+      type: macro-f1
+      value: 61.86
+    - name: 5-shot
+      type: macro-f1
+      value: 66.99
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - name: 0-shot
+      type: bleu
+      value: 18.43
+    - name: 1-shot
+      type: bleu
+      value: 28.25
+    - name: 3-shot
+      type: bleu
+      value: 29.45
+    - 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: 2.8
+    - name: 1-shot
+      type: bleu
+      value: 2.9
+    - name: 3-shot
+      type: bleu
+      value: 6.63
+    - name: 5-shot
+      type: bleu
+      value: 12.04
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_EM
+      type: XQuAD_EM
+    metrics:
+    - name: 0-shot
+      type: exact_match
+      value: 5.04
+    - name: 1-shot
+      type: exact_match
+      value: 22.44
+    - name: 3-shot
+      type: exact_match
+      value: 30.42
+    - name: 5-shot
+      type: exact_match
+      value: 35.71
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_F1
+      type: XQuAD_F1
+    metrics:
+    - name: 0-shot
+      type: f1
+      value: 23.36
+    - name: 1-shot
+      type: f1
+      value: 44.63
+    - name: 3-shot
+      type: f1
+      value: 54.78
+    - name: 5-shot
+      type: f1
+      value: 60.43
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: 0-shot
+      type: spearman
+      value: 73.38
+    - name: 1-shot
+      type: spearman
+      value: 78.93
+    - name: 3-shot
+      type: spearman
+      value: 79.68
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - name: 0-shot
+      type: pearson
+      value: 73.93
+    - name: 1-shot
+      type: pearson
+      value: 77.69
+    - name: 3-shot
+      type: pearson
+      value: 78.17
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+RoMistral is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **human alignedinstruct 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:** [RoMistral-7b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09)
+- **Trained using:** [RoHelpSteer](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_helpsteer)
+
+
+<!-- - **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-DPO")
+model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct-DPO")
+
+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><strong>51.61</strong></center></td><td><center>66.48</center></td><td><center>60.27</center></td><td><center><strong>34.19</strong></center></td><td><center>52.30</center></td>
+</tr>
+<tr>
+<td>RoMistral-7b-Instruct-2024-10-09</td><td><center><strong>52.91</strong></center></td><td><center><strong>52.27</strong></center></td><td><center>49.33</center></td><td><center><strong>70.03</strong></center></td><td><center><strong>62.88</strong></center></td><td><center>32.42</center></td><td><center>50.51</center></td>
+</tr>
+<tr>
+<td><em>RoMistral-7b-Instruct-DPO-2024-10-09</em></td><td><center><em>51.95</em></center></td><td><center><em>50.73</em></center></td><td><center><em>47.88</em></center></td><td><center><em>68.41</em></center></td><td><center><em>62.27</em></center></td><td><center><em>32.27</em></center></td><td><center><em>50.12</em></center></td>
+</tr>
+</tbody>
+</table>
+
+## Downstream tasks
+
+<table>
+<tbody>
+<tr>
+<td></td>
+<td colspan="4"><center><strong>LaRoSeDa</strong></center></td>
+<td colspan="4"><center><strong>WMT</strong></center></td>
+</tr>
+<tr>
+<td></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+</tr>
+<tr>
+<td><strong>Model</strong></td>
+<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
+<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
+<td><center><strong>Binary<br>(Macro F1)</strong></center></td>
+<td><center><strong>Multiclass<br>(Macro F1)</strong></center></td>
+<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
+<td><center><strong>RO-EN<br>(Bleu)</strong></center></td>
+<td><center><strong>EN-RO<br>(Bleu)</strong></center></td>
+<td><center><strong>RO-EN<br>(Bleu)</strong></center>
+</tr>
+<tr>
+<td>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><strong>97.36</strong></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><strong>28.28</strong></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-DPO-2024-10-09</em></td><td><center><em>82.13</em></center></td><td><center><em>65.24</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>26.25</em></center></td><td><center><em>6.09</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
+</tr>
+</tbody>
+</table>
+
+
+<table>
+<tbody>
+<tr>
+<td></td>
+<td colspan="4"><center><strong>XQuAD</strong></center></td>
+<td colspan="4"><center><strong>STS</strong></center></td>
+</tr>
+<tr>
+<td></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+<td colspan="2"><center><strong>Few-shot</strong></center></td>
+<td colspan="2"><center><strong>Finetuned</strong></center></td>
+</tr>
+<tr>
+<td><strong>Model</strong></td>
+<td><center><strong>(EM)</strong></center></td>
+<td><center><strong>(F1)</strong></center></td>
+<td><center><strong>(EM)</strong></center></td>
+<td><center><strong>(F1)</strong></center></td>
+<td><center><strong>(Spearman)</strong></center></td>
+<td><center><strong>(Pearson)</strong></center></td>
+<td><center><strong>(Spearman)</strong></center></td>
+<td><center><strong>(Pearson)</strong></center></td>
+</tr>
+<tr>
+<td>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><strong>43.66</strong></center></td><td><center><strong>63.70</strong></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><strong>78.47</strong></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-DPO-2024-10-09</em></td><td><center><em>23.40</em></center></td><td><center><em>45.80</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>77.33</em></center></td><td><center><em>76.60</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></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-DPO-2024-10-09</em></td><td><center><em><strong>5.88</strong></em></center></td><td><center><em><strong>6.44</strong></em></center></td><td><center><em><strong>5.33</strong></em></center></td><td><center><em><strong>160/160</strong></em></center></td>
+</tr>
+</tbody>
+</table>
+
+
+## RoCulturaBench
+
+<table>
+<tbody>
+<tr>
+<td><strong>Model</strong></td>
+<td><strong><center>Average</center></strong></td>
+<td><strong><center>Answers in Ro</center></strong></td>
+</tr>
+<tr>
+<td>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-DPO-2024-10-09</em></td><td><center><em><strong>4.72</strong></em></center></td><td><center><em><strong>100/100</strong></em></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-DPO-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-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:**
+
+[More Information Needed]  -->