|
--- |
|
license: cc-by-nc-4.0 |
|
language: |
|
- ro |
|
base_model: |
|
- meta-llama/Llama-3.1-8B-Instruct |
|
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/RoLlama3.1-8b-Instruct-2024-10-09 |
|
results: |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoMT-Bench |
|
type: RoMT-Bench |
|
metrics: |
|
- name: Score |
|
type: Score |
|
value: 5.42 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoCulturaBench |
|
type: RoCulturaBench |
|
metrics: |
|
- name: Score |
|
type: Score |
|
value: 3.55 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: Romanian_Academic_Benchmarks |
|
type: Romanian_Academic_Benchmarks |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 53.03 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 47.69 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 54.57 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 65.84 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 59.94 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 44.30 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_truthfulqa |
|
type: OpenLLM-Ro/ro_truthfulqa |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 45.82 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary |
|
type: LaRoSeDa_binary |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 94.56 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 60.10 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary_finetuned |
|
type: LaRoSeDa_binary_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 95.12 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass_finetuned |
|
type: LaRoSeDa_multiclass_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 87.53 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 21.88 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 23.99 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO_finetuned |
|
type: WMT_EN-RO_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 28.27 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN_finetuned |
|
type: WMT_RO-EN_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 40.44 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 13.59 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 23.56 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 49.41 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 62.93 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 75.89 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 76.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 86.86 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 87.05 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: RoMT-Bench |
|
type: RoMT-Bench |
|
metrics: |
|
- name: First turn |
|
type: Score |
|
value: 5.95 |
|
- name: Second turn |
|
type: Score |
|
value: 4.89 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 42.76 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 46.44 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 48.24 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 48.84 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 49.36 |
|
- name: 25-shot |
|
type: accuracy |
|
value: 50.47 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 52.95 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 54.62 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 55.54 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 55.17 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 64.40 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 66.14 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 65.75 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 67.09 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 59.07 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 59.26 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 60.41 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 60.18 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 60.77 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: 1-shot |
|
type: accuracy |
|
value: 35.10 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 47.01 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 50.80 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary |
|
type: LaRoSeDa_binary |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 90.18 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 94.45 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 96.36 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 97.27 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 67.56 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 63.21 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 51.69 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 57.95 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 5.12 |
|
- name: 1-shot |
|
type: bleu |
|
value: 26.99 |
|
- name: 3-shot |
|
type: bleu |
|
value: 27.91 |
|
- name: 5-shot |
|
type: bleu |
|
value: 27.51 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 1.63 |
|
- name: 1-shot |
|
type: bleu |
|
value: 22.59 |
|
- name: 3-shot |
|
type: bleu |
|
value: 35.70 |
|
- name: 5-shot |
|
type: bleu |
|
value: 36.05 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_EM |
|
type: XQuAD_EM |
|
metrics: |
|
- name: 0-shot |
|
type: exact_match |
|
value: 6.55 |
|
- name: 1-shot |
|
type: exact_match |
|
value: 38.32 |
|
- name: 3-shot |
|
type: exact_match |
|
value: 8.66 |
|
- name: 5-shot |
|
type: exact_match |
|
value: 0.84 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_F1 |
|
type: XQuAD_F1 |
|
metrics: |
|
- name: 0-shot |
|
type: f1 |
|
value: 16.04 |
|
- name: 1-shot |
|
type: f1 |
|
value: 56.16 |
|
- name: 3-shot |
|
type: f1 |
|
value: 15.64 |
|
- name: 5-shot |
|
type: f1 |
|
value: 6.39 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Spearman |
|
type: STS_Spearman |
|
metrics: |
|
- name: 1-shot |
|
type: spearman |
|
value: 76.27 |
|
- name: 3-shot |
|
type: spearman |
|
value: 75.48 |
|
- name: 5-shot |
|
type: spearman |
|
value: 75.92 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Pearson |
|
type: STS_Pearson |
|
metrics: |
|
- name: 1-shot |
|
type: pearson |
|
value: 76.76 |
|
- name: 3-shot |
|
type: pearson |
|
value: 75.38 |
|
- name: 5-shot |
|
type: pearson |
|
value: 75.87 |
|
|
|
|
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
*Built with Meta Llama 3.1* |
|
|
|
This model points/is identical to [RoLlama3.1-8b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09). |
|
|
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
RoLlama3.1 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **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:** [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) |
|
- **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 |
|
|
|
RoLlama3.1 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/RoLlama3.1-8b-Instruct") |
|
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama3.1-8b-Instruct") |
|
|
|
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-3.1-8B-Instruct</td><td><center>49.87</center></td><td><center>42.86</center></td><td><center>53.73</center></td><td><center>59.71</center></td><td><center>56.82</center></td><td><center>35.56</center></td><td><center><strong>50.54</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3.1-8b-Instruct-2024-10-09</em></td><td><center><em><strong>53.03</strong></em></center></td><td><center><em><strong>47.69</strong></em></center></td><td><center><em>54.57</em></center></td><td><center><em>65.84</em></center></td><td><center><em><strong>59.94</strong></em></center></td><td><center><em><strong>44.30</strong></em></center></td><td><center><em>45.82</em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3.1-8b-Instruct-DPO-2024-10-09</td><td><center>52.74</center></td><td><center>44.84</center></td><td><center><strong>55.06</strong></center></td><td><center><strong>65.87</strong></center></td><td><center>58.67</center></td><td><center>44.17</center></td><td><center>47.82</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-3.1-8B-Instruct</td><td><center>95.74</center></td><td><center>59.49</center></td><td><center><strong>98.57</strong></center></td><td><center>82.41</center></td><td><center>19.01</center></td><td><center><strong>27.77</strong></center></td><td><center><strong>29.02</strong></center></td><td><center>39.80</center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3.1-8b-Instruct-2024-10-09</em></td><td><center><em>94.56</em></center></td><td><center><em><strong>60.10</strong></em></center></td><td><center><em>95.12</em></center></td><td><center><em><strong>87.53</strong></em></center></td><td><center><em><strong>21.88</strong></em></center></td><td><center><em>23.99</em></center></td><td><center><em>28.27</em></center></td><td><center><em><strong>40.44</strong></em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3.1-8b-Instruct-DPO-2024-10-09</td><td><center><strong>96.10</strong></center></td><td><center>55.37</center></td><td><center>-</center></td><td><center>-</center></td><td><center>21.29</center></td><td><center>21.86</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-3.1-8B-Instruct</td><td><center><strong>44.96</strong></center></td><td><center><strong>64.45</strong></center></td><td><center><strong>69.50</strong></center></td><td><center><strong>84.31</strong></center></td><td><center>72.11</center></td><td><center>71.64</center></td><td><center>84.59</center></td><td><center>84.96</center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3.1-8b-Instruct-2024-10-09</em></td><td><center><em>13.59</em></center></td><td><center><em>23.56</em></center></td><td><center><em>49.41</em></center></td><td><center><em>62.93</em></center></td><td><center><em>75.89</em></center></td><td><center><em>76.00</em></center></td><td><center><em><strong>86.86</strong></em></center></td><td><center><em><strong>87.05</strong></em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3.1-8b-Instruct-DPO-2024-10-09</td><td><center>21.58</center></td><td><center>36.54</center></td><td><center>-</center></td><td><center>-</center></td><td><center><strong>78.01</strong></center></td><td><center><strong>77.98</strong></center></td><td><center>-</center></td><td><center>-</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-3.1-8B-Instruct</td><td><center>5.69</center></td><td><center>5.85</center></td><td><center>5.53</center></td><td><center><strong>160/160</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3.1-8b-Instruct-2024-10-09</em></td><td><center><em>5.42</em></center></td><td><center><em>5.95</em></center></td><td><center><em>4.89</em></center></td><td><center><em><strong>160/160</strong></em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3.1-8b-Instruct-DPO-2024-10-09</td><td><center><strong>6.21</strong></center></td><td><center><strong>6.74</strong></center></td><td><center><strong>5.69</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-3.1-8B-Instruct</td><td><center>3.54</center></td><td><center><strong>100/100</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama3.1-8b-Instruct-2024-10-09</em></td><td><center><em>3.55</em></center></td><td><center><em><strong>100/100</strong></em></center></td> |
|
</tr> |
|
<tr> |
|
<td>RoLlama3.1-8b-Instruct-DPO-2024-10-09</td><td><center><strong>4.42</strong></center></td><td><center><strong>100/100</strong></center></td> |
|
</tr> |
|
</tbody> |
|
</table> |
|
|
|
|
|
|
|
## RoLlama3.1 Model Family |
|
|
|
| Model | Link | |
|
|--------------------|:--------:| |
|
|*RoLlama3.1-8b-Instruct-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09) | |
|
|RoLlama3.1-8b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-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] --> |
