|
--- |
|
license: cc-by-nc-4.0 |
|
language: |
|
- ro |
|
base_model: |
|
- OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09 |
|
datasets: |
|
- OpenLLM-Ro/ro_dpo_helpsteer |
|
model-index: |
|
- name: OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2024-10-09 |
|
results: |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoMT-Bench |
|
type: RoMT-Bench |
|
metrics: |
|
- name: Score |
|
type: Score |
|
value: 5.87 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoCulturaBench |
|
type: RoCulturaBench |
|
metrics: |
|
- name: Score |
|
type: Score |
|
value: 4.40 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: Romanian_Academic_Benchmarks |
|
type: Romanian_Academic_Benchmarks |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 49.96 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 46.29 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 53.29 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 65.57 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 58.15 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 34.77 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_truthfulqa |
|
type: OpenLLM-Ro/ro_truthfulqa |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 41.70 |
|
- 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: 54.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary_finetuned |
|
type: LaRoSeDa_binary_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass_finetuned |
|
type: LaRoSeDa_multiclass_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 22.09 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 23.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO_finetuned |
|
type: WMT_EN-RO_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN_finetuned |
|
type: WMT_RO-EN_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 26.05 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 42.77 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 79.64 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 79.52 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 0.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoMT-Bench |
|
type: RoMT-Bench |
|
metrics: |
|
- name: First turn |
|
type: Score |
|
value: 6.22 |
|
- name: Second turn |
|
type: Score |
|
value: 5.49 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 44.56 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 45.42 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 46.10 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 46.27 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 46.96 |
|
- name: 25-shot |
|
type: accuracy |
|
value: 48.41 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 52.33 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 52.86 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 54.06 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 53.90 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 64.33 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 64.72 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 66.30 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 66.93 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 57.45 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 57.65 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 58.18 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 58.64 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 58.85 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: 1-shot |
|
type: accuracy |
|
value: 32.52 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 33.97 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 37.83 |
|
- 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: 97.07 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 97.40 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 97.80 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 58.49 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 55.93 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 47.70 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 53.89 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 8.63 |
|
- name: 1-shot |
|
type: bleu |
|
value: 25.89 |
|
- name: 3-shot |
|
type: bleu |
|
value: 26.79 |
|
- name: 5-shot |
|
type: bleu |
|
value: 27.05 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 3.56 |
|
- name: 1-shot |
|
type: bleu |
|
value: 20.66 |
|
- name: 3-shot |
|
type: bleu |
|
value: 33.56 |
|
- name: 5-shot |
|
type: bleu |
|
value: 34.22 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_EM |
|
type: XQuAD_EM |
|
metrics: |
|
- name: 0-shot |
|
type: exact_match |
|
value: 11.26 |
|
- name: 1-shot |
|
type: exact_match |
|
value: 34.29 |
|
- name: 3-shot |
|
type: exact_match |
|
value: 29.24 |
|
- name: 5-shot |
|
type: exact_match |
|
value: 29.41 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_F1 |
|
type: XQuAD_F1 |
|
metrics: |
|
- name: 0-shot |
|
type: f1 |
|
value: 22.98 |
|
- name: 1-shot |
|
type: f1 |
|
value: 54.48 |
|
- name: 3-shot |
|
type: f1 |
|
value: 46.18 |
|
- name: 5-shot |
|
type: f1 |
|
value: 47.43 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Spearman |
|
type: STS_Spearman |
|
metrics: |
|
- name: 1-shot |
|
type: spearman |
|
value: 79.99 |
|
- name: 3-shot |
|
type: spearman |
|
value: 78.42 |
|
- name: 5-shot |
|
type: spearman |
|
value: 80.51 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Pearson |
|
type: STS_Pearson |
|
metrics: |
|
- name: 1-shot |
|
type: pearson |
|
value: 80.59 |
|
- name: 3-shot |
|
type: pearson |
|
value: 78.11 |
|
- name: 5-shot |
|
type: pearson |
|
value: 79.87 |
|
|
|
|
|
|
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
*Built with Meta Llama 3* |
|
|
|
This model points/is identical to [RoLlama3-8b-Instruct-DPO-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2024-10-09). |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
RoLlama3 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **human aligned instruct 8B 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:** [RoLlama3-8b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-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 |
|
|
|
RoLlama3 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/RoLlama3-8b-Instruct-DPO-2024-10-09") |
|
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama3-8b-Instruct-DPO-2024-10-09") |
|
|
|
instruction = "Ce jocuri de societate pot juca cu prietenii mei?" |
|
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, 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>Llama-3-8B-Instruct</td><td><center>50.62</center></td><td><center>43.69</center></td><td><center>52.04</center></td><td><center>59.33</center></td><td><center>53.19</center></td><td><center><strong>43.87</strong></center></td><td><center><strong>51.59</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>50.56</center></td><td><center>44.70</center></td><td><center>52.19</center></td><td><center><strong>67.23</strong></center></td><td><center>57.69</center></td><td><center>30.23</center></td><td><center>51.34</center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center><strong>52.21</strong></center></td><td><center><strong>47.94</strong></center></td><td><center><strong>53.50</strong></center></td><td><center>66.06</center></td><td><center><strong>59.72</strong></center></td><td><center>40.16</center></td><td><center>45.90</center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3-8b-Instruct-DPO-2024-10-09</em></td><td><center><em>49.96</em></center></td><td><center><em>46.29</em></center></td><td><center><em>53.29</em></center></td><td><center><em>65.57</em></center></td><td><center><em>58.15</em></center></td><td><center><em>34.77</em></center></td><td><center><em>41.70</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>Llama-3-8B-Instruct</td><td><center>95.88</center></td><td><center>56.21</center></td><td><center><strong>98.53</strong></center></td><td><center>86.19</center></td><td><center>18.88</center></td><td><center><strong>30.98</strong></center></td><td><center><strong>28.02</strong></center></td><td><center>40.28</center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center><strong>97.52</strong></center></td><td><center><strong>67.41</strong></center></td><td><center>94.15</center></td><td><center>87.13</center></td><td><center><strong>24.01</strong></center></td><td><center>27.36</center></td><td><center>26.53</center></td><td><center>40.36</center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>95.58</center></td><td><center>61.20</center></td><td><center>96.46</center></td><td><center><strong>87.26</strong></center></td><td><center>22.92</center></td><td><center>24.28</center></td><td><center>27.31</center></td><td><center><strong>40.52</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3-8b-Instruct-DPO-2024-10-09</em></td><td><center><em>97.48</em></center></td><td><center><em>54.00</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>22.09</em></center></td><td><center><em>23.00</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>Llama-3-8B-Instruct</td><td><center><strong>39.47</strong></center></td><td><center>58.67</center></td><td><center><strong>67.65</strong></center></td><td><center><strong>82.77</strong></center></td><td><center>73.04</center></td><td><center>72.36</center></td><td><center>83.49</center></td><td><center>84.06</center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>39.43</center></td><td><center><strong>59.50</strong></center></td><td><center>44.45</center></td><td><center>59.76</center></td><td><center>77.20</center></td><td><center>77.87</center></td><td><center>85.80</center></td><td><center>86.05</center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>18.89</center></td><td><center>31.79</center></td><td><center>50.84</center></td><td><center>65.18</center></td><td><center>77.60</center></td><td><center>76.86</center></td><td><center><strong>86.70</strong></center></td><td><center><strong>87.09</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3-8b-Instruct-DPO-2024-10-09</em></td><td><center><em>26.05</em></center></td><td><center><em>42.77</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>79.64</strong></em></center></td><td><center><em><strong>79.52</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>Llama-3-8B-Instruct</td><td><center><strong>5.96</strong></center></td><td><center>6.16</center></td><td><center><strong>5.76</strong></center></td><td><center>158/160</center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>5.15</center></td><td><center>6.03</center></td><td><center>4.28</center></td><td><center><strong>160/160</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>5.38</center></td><td><center>6.09</center></td><td><center>4.67</center></td><td><center><strong>160/160</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3-8b-Instruct-DPO-2024-10-09</em></td><td><center><em>5.87</em></center></td><td><center><em><strong>6.22</strong></em></center></td><td><center><em>5.49</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>Llama-3-8B-Instruct</td><td><center><strong>4.62</strong></center></td><td><center><strong>100/100</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-06-28</td><td><center>3.71</center></td><td><center><strong>100/100</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3-8b-Instruct-2024-10-09</td><td><center>3.81</center></td><td><center><strong>100/100</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3-8b-Instruct-DPO-2024-10-09</em></td><td><center><em>4.40</em></center></td><td><center><em><strong>100/100</strong></em></center></td> |
|
</tr> |
|
</tbody> |
|
</table> |
|
|
|
|
|
|
|
## RoLlama3 Model Family |
|
|
|
| Model | Link | |
|
|--------------------|:--------:| |
|
|RoLlama3-8b-Instruct-2024-06-28| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28) | |
|
|RoLlama3-8b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-10-09) | |
|
|*RoLlama3-8b-Instruct-DPO-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-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] --> |
