|
--- |
|
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 |
|
model-index: |
|
- name: OpenLLM-Ro/RoLlama2-7b-Instruct-2024-05-14 |
|
results: |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoMT-Bench |
|
type: RoMT-Bench |
|
metrics: |
|
- name: Score |
|
type: Score |
|
value: 3.86 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoCulturaBench |
|
type: RoCulturaBench |
|
metrics: |
|
- name: Score |
|
type: Score |
|
value: 3.77 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: Romanian_Academic_Benchmarks |
|
type: Romanian_Academic_Benchmarks |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 45.71 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 43.66 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 39.70 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 70.34 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 57.36 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 18.78 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_truthfulqa |
|
type: OpenLLM-Ro/ro_truthfulqa |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 44.44 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary |
|
type: LaRoSeDa_binary |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 97.48 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 65.26 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary_finetuned |
|
type: LaRoSeDa_binary_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 98.83 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass_finetuned |
|
type: LaRoSeDa_multiclass_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 87.28 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 27.38 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 10.32 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO_finetuned |
|
type: WMT_EN-RO_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 27.59 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN_finetuned |
|
type: WMT_RO-EN_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 40.13 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 44.52 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 64.75 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 54.96 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 70.20 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 65.50 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 67.79 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 84.44 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 84.76 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoMT-Bench |
|
type: RoMT-Bench |
|
metrics: |
|
- name: First turn |
|
type: Score |
|
value: 4.67 |
|
- name: Second turn |
|
type: Score |
|
value: 3.04 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 41.73 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 42.16 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 43.53 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 44.90 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 44.99 |
|
- name: 25-shot |
|
type: accuracy |
|
value: 44.64 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 38.54 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 39.36 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 40.82 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 40.07 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 72.61 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 69.93 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 70.40 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 68.43 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 56.90 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 57.07 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 57.56 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 57.35 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 57.93 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: 1-shot |
|
type: accuracy |
|
value: 11.22 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 21.38 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 23.73 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary |
|
type: LaRoSeDa_binary |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 97.67 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 96.77 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 97.60 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 97.87 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 61.82 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 58.84 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 68.67 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 71.71 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 19.71 |
|
- name: 1-shot |
|
type: bleu |
|
value: 29.62 |
|
- name: 3-shot |
|
type: bleu |
|
value: 30.11 |
|
- name: 5-shot |
|
type: bleu |
|
value: 30.10 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 1.86 |
|
- name: 1-shot |
|
type: bleu |
|
value: 4.41 |
|
- name: 3-shot |
|
type: bleu |
|
value: 14.95 |
|
- name: 5-shot |
|
type: bleu |
|
value: 20.07 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_EM |
|
type: XQuAD_EM |
|
metrics: |
|
- name: 0-shot |
|
type: exact_match |
|
value: 34.87 |
|
- name: 1-shot |
|
type: exact_match |
|
value: 44.96 |
|
- name: 3-shot |
|
type: exact_match |
|
value: 48.40 |
|
- name: 5-shot |
|
type: exact_match |
|
value: 49.83 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_F1 |
|
type: XQuAD_F1 |
|
metrics: |
|
- name: 0-shot |
|
type: f1 |
|
value: 58.07 |
|
- name: 1-shot |
|
type: f1 |
|
value: 63.93 |
|
- name: 3-shot |
|
type: f1 |
|
value: 67.89 |
|
- name: 5-shot |
|
type: f1 |
|
value: 69.10 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Spearman |
|
type: STS_Spearman |
|
metrics: |
|
- name: 1-shot |
|
type: spearman |
|
value: 61.14 |
|
- name: 3-shot |
|
type: spearman |
|
value: 66.91 |
|
- name: 5-shot |
|
type: spearman |
|
value: 68.46 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Pearson |
|
type: STS_Pearson |
|
metrics: |
|
- name: 1-shot |
|
type: pearson |
|
value: 61.88 |
|
- name: 3-shot |
|
type: pearson |
|
value: 70.04 |
|
- name: 5-shot |
|
type: pearson |
|
value: 71.46 |
|
|
|
|
|
--- |
|
|
|
# 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) |
|
|
|
### Model Sources |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Repository:** https://github.com/OpenLLM-Ro/llama-recipes |
|
- **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-2024-05-14") |
|
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct-2024-05-14") |
|
|
|
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><em>RoLlama2-7b-Instruct-2024-05-14</em></td><td><center><em><strong>45.71</strong></em></center></td><td><center><em>43.66</em></center></td><td><center><em>39.70</em></center></td><td><center><em><strong>70.34</strong></em></center></td><td><center><em>57.36</em></center></td><td><center><em><strong>18.78</strong></em></center></td><td><center><em>44.44</em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center>44.50</center></td><td><center><strong>44.73</strong></center></td><td><center><strong>40.39</strong></center></td><td><center>63.67</center></td><td><center>59.12</center></td><td><center>13.29</center></td><td><center><strong>45.78</strong></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><em>RoLlama2-7b-Instruct-2024-05-14</em></td><td><center><em>97.48</em></center></td><td><center><em><strong>65.26</strong></em></center></td><td><center><em><strong>98.83</strong></em></center></td><td><center><em><strong>87.28</strong></em></center></td><td><center><em><strong>27.38</strong></em></center></td><td><center><em>10.32</em></center></td><td><center><em>27.59</em></center></td><td><center><em><strong>40.13</strong></em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center><strong>97.66</strong></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>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><em>RoLlama2-7b-Instruct-2024-05-14</em></td><td><center><em>44.52</em></center></td><td><center><em>64.75</em></center></td><td><center><em>54.96</em></center></td><td><center><em>70.20</em></center></td><td><center><em><strong>65.50</strong></em></center></td><td><center><em><strong>67.79</strong></em></center></td><td><center><em>84.44</em></center></td><td><center><em>84.76</em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama2-7b-Instruct-2024-10-09</td><td><center><strong>45.71</strong></center></td><td><center><strong>65.08</strong></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>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><em>RoLlama2-7b-Instruct-2024-05-14</em></td><td><center><em>3.86</em></center></td><td><center><em>4.67</em></center></td><td><center><em>3.04</em></center></td><td><center><em><strong>160/160</strong></em></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>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><em>RoLlama2-7b-Instruct-2024-05-14</em></td><td><center><em>3.77</em></center></td><td><center><em><strong>100/100</strong></em></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>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:** |
|
|
|
[More Information Needed] --> |
