Update README.md

README.md

@@ -1,3 +1,655 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+language:
+- ro
+base_model:
+- OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09
+datasets:
+- OpenLLM-Ro/ro_dpo_helpsteer
+model-index:
+    - name: OpenLLM-Ro/RoGemma2-9b-Instruct-DPO-2024-10-09
+      results:
+        - task:
+            type: text-generation
+          dataset:
+            name: RoMT-Bench
+            type: RoMT-Bench
+          metrics:
+            - name: Score
+              type: Score
+              value: 6.77
+        - task:
+            type: text-generation
+          dataset:
+            name: RoCulturaBench
+            type: RoCulturaBench
+          metrics:
+            - name: Score
+              type: Score
+              value: 4.83
+        - task:
+            type: text-generation
+          dataset:
+            name: Romanian_Academic_Benchmarks
+            type: Romanian_Academic_Benchmarks
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 59.08
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_arc_challenge
+            type: OpenLLM-Ro/ro_arc_challenge
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 54.10
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_mmlu
+            type: OpenLLM-Ro/ro_mmlu
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 63.41
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_winogrande
+            type: OpenLLM-Ro/ro_winogrande
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 70.02
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_hellaswag
+            type: OpenLLM-Ro/ro_hellaswag
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 59.35
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_gsm8k
+            type: OpenLLM-Ro/ro_gsm8k
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 57.24
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_truthfulqa
+            type: OpenLLM-Ro/ro_truthfulqa
+          metrics:
+            - name: Average accuracy
+              type: accuracy
+              value: 50.39
+        - task:
+            type: text-generation
+          dataset:
+            name: LaRoSeDa_binary
+            type: LaRoSeDa_binary
+          metrics:
+            - name: Average macro-f1
+              type: macro-f1
+              value: 97.74
+        - task:
+            type: text-generation
+          dataset:
+            name: LaRoSeDa_multiclass
+            type: LaRoSeDa_multiclass
+          metrics:
+            - name: Average macro-f1
+              type: macro-f1
+              value: 67.40
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_EN-RO
+            type: WMT_EN-RO
+          metrics:
+            - name: Average bleu
+              type: bleu
+              value: 27.32
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_RO-EN
+            type: WMT_RO-EN
+          metrics:
+            - name: Average bleu
+              type: bleu
+              value: 15.96
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD
+            type: XQuAD
+          metrics:
+            - name: Average exact_match
+              type: exact_match
+              value: 32.42
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD
+            type: XQuAD
+          metrics:
+            - name: Average f1
+              type: f1
+              value: 58.68
+        - task:
+            type: text-generation
+          dataset:
+            name: STS
+            type: STS
+          metrics:
+            - name: Average spearman
+              type: spearman
+              value: 80.82
+        - task:
+            type: text-generation
+          dataset:
+            name: STS
+            type: STS
+          metrics:
+            - name: Average pearson
+              type: pearson
+              value: 81.50
+        - task:
+            type: text-generation
+          dataset:
+            name: RoMT-Bench
+            type: RoMT-Bench
+          metrics:
+            - name: First turn
+              type: Score
+              value: 7.24
+            - name: Second turn
+              type: Score
+              value: 6.30
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_arc_challenge
+            type: OpenLLM-Ro/ro_arc_challenge
+          metrics:
+            - name: 0-shot 
+              type: accuracy
+              value: 51.59
+            - name: 1-shot 
+              type: accuracy
+              value: 50.99
+            - name: 3-shot 
+              type: accuracy
+              value: 53.47
+            - name: 5-shot 
+              type: accuracy
+              value: 54.84
+            - name: 10-shot 
+              type: accuracy
+              value: 58.10
+            - name: 25-shot 
+              type: accuracy
+              value: 55.61
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_mmlu
+            type: OpenLLM-Ro/ro_mmlu
+          metrics:
+            - name: 0-shot 
+              type: accuracy
+              value: 62.15
+            - name: 1-shot 
+              type: accuracy
+              value: 62.78
+            - name: 3-shot 
+              type: accuracy
+              value: 64.27
+            - name: 5-shot 
+              type: accuracy
+              value: 64.43
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_winogrande
+            type: OpenLLM-Ro/ro_winogrande
+          metrics:
+            - name: 0-shot 
+              type: accuracy
+              value: 66.69
+            - name: 1-shot 
+              type: accuracy
+              value: 68.82
+            - name: 3-shot 
+              type: accuracy
+              value: 71.82
+            - name: 5-shot 
+              type: accuracy
+              value: 72.77
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_hellaswag
+            type: OpenLLM-Ro/ro_hellaswag
+          metrics:
+            - name: 0-shot 
+              type: accuracy
+              value: 56.98
+            - name: 1-shot 
+              type: accuracy
+              value: 57.73
+            - name: 3-shot 
+              type: accuracy
+              value: 59.29
+            - name: 5-shot 
+              type: accuracy
+              value: 60.70
+            - name: 10-shot 
+              type: accuracy
+              value: 62.03
+        - task:
+            type: text-generation
+          dataset:
+            name: OpenLLM-Ro/ro_gsm8k
+            type: OpenLLM-Ro/ro_gsm8k
+          metrics:
+            - name: 1-shot 
+              type: accuracy
+              value: 46.78
+            - name: 3-shot 
+              type: accuracy
+              value: 59.97
+            - name: 5-shot 
+              type: accuracy
+              value: 64.97
+        - task:
+            type: text-generation
+          dataset:
+            name: LaRoSeDa_binary
+            type: LaRoSeDa_binary
+          metrics:
+            - name: 0-shot 
+              type: macro-f1
+              value: 97.30
+            - name: 1-shot 
+              type: macro-f1
+              value: 97.50
+            - name: 3-shot 
+              type: macro-f1
+              value: 97.83
+            - name: 5-shot 
+              type: macro-f1
+              value: 98.33
+        - task:
+            type: text-generation
+          dataset:
+            name: LaRoSeDa_multiclass
+            type: LaRoSeDa_multiclass
+          metrics:
+            - name: 0-shot 
+              type: macro-f1
+              value: 59.30
+            - name: 1-shot 
+              type: macro-f1
+              value: 65.52
+            - name: 3-shot 
+              type: macro-f1
+              value: 70.94
+            - name: 5-shot 
+              type: macro-f1
+              value: 73.85
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_EN-RO
+            type: WMT_EN-RO
+          metrics:
+            - name: 0-shot 
+              type: bleu
+              value: 17.49
+            - name: 1-shot 
+              type: bleu
+              value: 30.33
+            - name: 3-shot 
+              type: bleu
+              value: 30.58
+            - name: 5-shot 
+              type: bleu
+              value: 30.88
+        - task:
+            type: text-generation
+          dataset:
+            name: WMT_RO-EN
+            type: WMT_RO-EN
+          metrics:
+            - name: 0-shot 
+              type: bleu
+              value: 2.17
+            - name: 1-shot 
+              type: bleu
+              value: 10.69
+            - name: 3-shot 
+              type: bleu
+              value: 21.68
+            - name: 5-shot 
+              type: bleu
+              value: 29.28
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD_EM
+            type: XQuAD_EM
+          metrics:
+            - name: 0-shot 
+              type: exact_match
+              value: 23.28
+            - name: 1-shot 
+              type: exact_match
+              value: 33.45
+            - name: 3-shot 
+              type: exact_match
+              value: 34.37
+            - name: 5-shot 
+              type: exact_match
+              value: 38.57
+        - task:
+            type: text-generation
+          dataset:
+            name: XQuAD_F1
+            type: XQuAD_F1
+          metrics:
+            - name: 0-shot 
+              type: f1
+              value: 47.16
+            - name: 1-shot 
+              type: f1
+              value: 60.28
+            - name: 3-shot 
+              type: f1
+              value: 62.09
+            - name: 5-shot 
+              type: f1
+              value: 65.20
+        - task:
+            type: text-generation
+          dataset:
+            name: STS_Spearman
+            type: STS_Spearman
+          metrics:
+            - name: 1-shot 
+              type: spearman
+              value: 75.34
+            - name: 3-shot 
+              type: spearman
+              value: 82.71
+            - name: 5-shot 
+              type: spearman
+              value: 84.41
+        - task:
+            type: text-generation
+          dataset:
+            name: STS_Pearson
+            type: STS_Pearson
+          metrics:
+            - name: 1-shot 
+              type: pearson
+              value: 77.97
+            - name: 3-shot 
+              type: pearson
+              value: 82.49
+            - name: 5-shot 
+              type: pearson
+              value: 84.05
+
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+This model points/is identical to [RoGemma2-9b-Instruct-DPO-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-DPO-2024-10-09).
+
+
+RoGemma2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **human aligned instruct 9B 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:** [RoGemma2-9b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09)
+- **Trained using:** [RoHelpSteer](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_helpsteer)
+
+
+### 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
+
+RoGemma2 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/RoGemma2-9b-Instruct-DPO")
+model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoGemma2-9b-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>gemma-2-9b-it</td><td><center>56.22</center></td><td><center>50.33</center></td><td><center><strong>64.01</strong></center></td><td><center>64.88</center></td><td><center><strong>63.11</strong></center></td><td><center>41.95</center></td><td><center>53.03</center></td>
+</tr>
+<tr>
+<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>57.06</center></td><td><center><strong>56.20</strong></center></td><td><center>62.98</center></td><td><center><strong>71.00</strong></center></td><td><center>60.52</center></td><td><center>37.86</center></td><td><center><strong>53.77</strong></center></td>
+</tr>
+<tr>
+<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em><strong>59.08</strong></em></center></td><td><center><em>54.10</em></center></td><td><center><em>63.41</em></center></td><td><center><em>70.02</em></center></td><td><center><em>59.35</em></center></td><td><center><em><strong>57.24</strong></em></center></td><td><center><em>50.39</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>gemma-2-9b-it</td><td><center>90.82</center></td><td><center>52.51</center></td><td><center>-</center></td><td><center>-</center></td><td><center>19.97</center></td><td><center><strong>28.94</strong></center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>96.19</center></td><td><center>62.49</center></td><td><center>-</center></td><td><center>-</center></td><td><center>25.74</center></td><td><center>23.16</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em><strong>97.74</strong></em></center></td><td><center><em><strong>67.40</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>27.32</strong></em></center></td><td><center><em>15.96</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>gemma-2-9b-it</td><td><center>37.56</center></td><td><center>57.48</center></td><td><center>-</center></td><td><center>-</center></td><td><center>71.39</center></td><td><center>71.73</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center><strong>51.37</strong></center></td><td><center><strong>70.74</strong></center></td><td><center>-</center></td><td><center>-</center></td><td><center>77.15</center></td><td><center>77.10</center></td><td><center>-</center></td><td><center>-</center></td>
+</tr>
+<tr>
+<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em>32.42</em></center></td><td><center><em>58.68</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>80.82</strong></em></center></td><td><center><em><strong>81.50</strong></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>gemma-2-9b-it</td><td><center><strong>7.50</strong></center></td><td><center><strong>7.91</strong></center></td><td><center><strong>7.09</strong></center></td><td><center>159/160</center></td>
+</tr>
+<tr>
+<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>6.08</center></td><td><center>6.78</center></td><td><center>5.39</center></td><td><center><strong>160/160</strong></center></td>
+</tr>
+<tr>
+<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em>6.77</em></center></td><td><center><em>7.24</em></center></td><td><center><em>6.30</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>gemma-2-9b-it</td><td><center><strong>5.68</strong></center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td>RoGemma2-9b-Instruct-2024-10-09</td><td><center>4.20</center></td><td><center><strong>100/100</strong></center></td>
+</tr>
+<tr>
+<td><em>RoGemma2-9b-Instruct-DPO-2024-10-09</em></td><td><center><em>4.83</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
+</tr>
+</tbody>
+</table>
+
+
+## RoGemma2 Model Family
+
+| Model              | Link  |
+|--------------------|:--------:|
+|RoGemma2-9b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09) |
+|*RoGemma2-9b-Instruct-DPO-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoGemma2-9b-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]  -->