OpenLLM-Ro/RoLlama3.1-8b-Instruct
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
af8e45291f4cf962fd6ce1fbafb847ac201b85ee
RoLlama3.1-8b-Instruct/README.md

707 lines
26 KiB
Markdown
Raw Normal View History

初始化项目，由ModelHub XC社区提供模型 Model: OpenLLM-Ro/RoLlama3.1-8b-Instruct Source: Original Platform
2026-07-28 09:54:13 +08:00
---
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
- OpenLLM-Ro/ro_sft_magpie_mt
- OpenLLM-Ro/ro_sft_magpie_reasoning
model-index:
- name: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23
results:
- task:
type: text-generation
dataset:
name: RoMT-Bench
type: RoMT-Bench
metrics:
- name: Score
type: Score
value: 6.43
- task:
type: text-generation
dataset:
name: RoCulturaBench
type: RoCulturaBench
metrics:
- name: Score
type: Score
value: 4.28
- task:
type: text-generation
dataset:
name: Romanian_Academic_Benchmarks
type: Romanian_Academic_Benchmarks
metrics:
- name: Average accuracy
type: accuracy
value: 53.36
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_arc_challenge
type: OpenLLM-Ro/ro_arc_challenge
metrics:
- name: Average accuracy
type: accuracy
value: 48.97
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_mmlu
type: OpenLLM-Ro/ro_mmlu
metrics:
- name: Average accuracy
type: accuracy
value: 55.17
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_winogrande
type: OpenLLM-Ro/ro_winogrande
metrics:
- name: Average accuracy
type: accuracy
value: 66.52
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_hellaswag
type: OpenLLM-Ro/ro_hellaswag
metrics:
- name: Average accuracy
type: accuracy
value: 60.73
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_gsm8k
type: OpenLLM-Ro/ro_gsm8k
metrics:
- name: Average accuracy
type: accuracy
value: 42.03
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_truthfulqa
type: OpenLLM-Ro/ro_truthfulqa
metrics:
- name: Average accuracy
type: accuracy
value: 46.71
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary
type: LaRoSeDa_binary
metrics:
- name: Average macro-f1
type: macro-f1
value: 95.32
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass
type: LaRoSeDa_multiclass
metrics:
- name: Average macro-f1
type: macro-f1
value: 60.84
- task:
type: text-generation
dataset:
name: WMT_EN-RO
type: WMT_EN-RO
metrics:
- name: Average bleu
type: bleu
value: 23.18
- task:
type: text-generation
dataset:
name: WMT_RO-EN
type: WMT_RO-EN
metrics:
- name: Average bleu
type: bleu
value: 25.11
- task:
type: text-generation
dataset:
name: XQuAD
type: XQuAD
metrics:
- name: Average exact_match
type: exact_match
value: 10.74
- task:
type: text-generation
dataset:
name: XQuAD
type: XQuAD
metrics:
- name: Average f1
type: f1
value: 19.75
- task:
type: text-generation
dataset:
name: STS
type: STS
metrics:
- name: Average spearman
type: spearman
value: 73.53
- task:
type: text-generation
dataset:
name: STS
type: STS
metrics:
- name: Average pearson
type: pearson
value: 74.93
- task:
type: text-generation
dataset:
name: RoMT-Bench
type: RoMT-Bench
metrics:
- name: First turn
type: Score
value: 6.78
- name: Second turn
type: Score
value: 6.09
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_arc_challenge
type: OpenLLM-Ro/ro_arc_challenge
metrics:
- name: 0-shot
type: accuracy
value: 45.24
- name: 1-shot
type: accuracy
value: 47.67
- name: 3-shot
type: accuracy
value: 49.36
- name: 5-shot
type: accuracy
value: 50.13
- name: 10-shot
type: accuracy
value: 50.81
- name: 25-shot
type: accuracy
value: 50.64
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_mmlu
type: OpenLLM-Ro/ro_mmlu
metrics:
- name: 0-shot
type: accuracy
value: 54.23
- name: 1-shot
type: accuracy
value: 56.36
- name: 3-shot
type: accuracy
value: 55.34
- name: 5-shot
type: accuracy
value: 54.74
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_winogrande
type: OpenLLM-Ro/ro_winogrande
metrics:
- name: 0-shot
type: accuracy
value: 64.96
- name: 1-shot
type: accuracy
value: 66.77
- name: 3-shot
type: accuracy
value: 67.09
- name: 5-shot
type: accuracy
value: 67.25
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_hellaswag
type: OpenLLM-Ro/ro_hellaswag
metrics:
- name: 0-shot
type: accuracy
value: 59.72
- name: 1-shot
type: accuracy
value: 60.30
- name: 3-shot
type: accuracy
value: 60.87
- name: 5-shot
type: accuracy
value: 61.14
- name: 10-shot
type: accuracy
value: 61.63
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_gsm8k
type: OpenLLM-Ro/ro_gsm8k
metrics:
- name: 1-shot
type: accuracy
value: 30.86
- name: 3-shot
type: accuracy
value: 43.90
- name: 5-shot
type: accuracy
value: 51.33
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary
type: LaRoSeDa_binary
metrics:
- name: 0-shot
type: macro-f1
value: 90.97
- name: 1-shot
type: macro-f1
value: 95.53
- name: 3-shot
type: macro-f1
value: 97.10
- name: 5-shot
type: macro-f1
value: 97.67
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass
type: LaRoSeDa_multiclass
metrics:
- name: 0-shot
type: macro-f1
value: 63.20
- name: 1-shot
type: macro-f1
value: 64.47
- name: 3-shot
type: macro-f1
value: 55.88
- name: 5-shot
type: macro-f1
value: 59.80
- task:
type: text-generation
dataset:
name: WMT_EN-RO
type: WMT_EN-RO
metrics:
- name: 0-shot
type: bleu
value: 4.92
- name: 1-shot
type: bleu
value: 28.01
- name: 3-shot
type: bleu
value: 30.16
- name: 5-shot
type: bleu
value: 29.61
- task:
type: text-generation
dataset:
name: WMT_RO-EN
type: WMT_RO-EN
metrics:
- name: 0-shot
type: bleu
value: 1.43
- name: 1-shot
type: bleu
value: 24.78
- name: 3-shot
type: bleu
value: 37.31
- name: 5-shot
type: bleu
value: 36.93
- task:
type: text-generation
dataset:
name: XQuAD_EM
type: XQuAD_EM
metrics:
- name: 0-shot
type: exact_match
value: 11.18
- name: 1-shot
type: exact_match
value: 26.47
- name: 3-shot
type: exact_match
value: 3.95
- name: 5-shot
type: exact_match
value: 1.34
- task:
type: text-generation
dataset:
name: XQuAD_F1
type: XQuAD_F1
metrics:
- name: 0-shot
type: f1
value: 25.76
- name: 1-shot
type: f1
value: 39.25
- name: 3-shot
type: f1
value: 8.40
- name: 5-shot
type: f1
value: 5.58
- task:
type: text-generation
dataset:
name: STS_Spearman
type: STS_Spearman
metrics:
- name: 1-shot
type: spearman
value: 73.52
- name: 3-shot
type: spearman
value: 74.02
- name: 5-shot
type: spearman
value: 73.06
- task:
type: text-generation
dataset:
name: STS_Pearson
type: STS_Pearson
metrics:
- name: 1-shot
type: pearson
value: 75.81
- name: 3-shot
type: pearson
value: 74.54
- name: 5-shot
type: pearson
value: 74.43
---
# Model Card for Model ID
*Built with Meta Llama 3.1*
This model points/is identical to [RoLlama3.1-8b-Instruct-2025-04-23](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23).
<!-- 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), [RoMagpiePro](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_mt), [RoMagpieReasoning](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_magpie_reasoning)
### 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>50.54</center></td>
</tr>
<tr>
<td>RoLlama3.1-8b-Instruct-2024-10-09</td><td><center>53.03</center></td><td><center>47.69</center></td><td><center>54.57</center></td><td><center>65.84</center></td><td><center>59.94</center></td><td><center><strong>44.30</strong></center></td><td><center>45.82</center></td>
</tr>
<tr>
<td><em>RoLlama3.1-8b-Instruct-2025-04-23</em></td><td><center><em>53.36</em></center></td><td><center><em>48.97</em></center></td><td><center><em>55.17</em></center></td><td><center><em>66.52</em></center></td><td><center><em><strong>60.73</strong></em></center></td><td><center><em>42.03</em></center></td><td><center><em>46.71</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>55.06</center></td><td><center>65.87</center></td><td><center>58.67</center></td><td><center>44.17</center></td><td><center>47.82</center></td>
</tr>
<tr>
<td>RoLlama3.1-8b-Instruct-DPO-2025-04-23</td><td><center><strong>53.76</strong></center></td><td><center><strong>51.09</strong></center></td><td><center><strong>56.22</strong></center></td><td><center><strong>66.77</strong></center></td><td><center>59.38</center></td><td><center>31.54</center></td><td><center><strong>57.56</strong></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>RoLlama3.1-8b-Instruct-2024-10-09</td><td><center>94.56</center></td><td><center>60.10</center></td><td><center>95.12</center></td><td><center><strong>87.53</strong></center></td><td><center>21.88</center></td><td><center>23.99</center></td><td><center>28.27</center></td><td><center><strong>40.44</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3.1-8b-Instruct-2025-04-23</em></td><td><center><em>95.32</em></center></td><td><center><em><strong>60.84</strong></em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em><strong>23.18</strong></em></center></td><td><center><em>25.11</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td>
</tr>
<tr>
<td>RoLlama3.1-8b-Instruct-DPO-2024-10-09</td><td><center>96.10</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>
<tr>
<td>RoLlama3.1-8b-Instruct-DPO-2025-04-23</td><td><center><strong>96.87</strong></center></td><td><center>60.75</center></td><td><center>-</center></td><td><center>-</center></td><td><center>20.30</center></td><td><center>18.57</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>RoLlama3.1-8b-Instruct-2024-10-09</td><td><center>13.59</center></td><td><center>23.56</center></td><td><center>49.41</center></td><td><center>62.93</center></td><td><center>75.89</center></td><td><center>76.00</center></td><td><center><strong>86.86</strong></center></td><td><center><strong>87.05</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3.1-8b-Instruct-2025-04-23</em></td><td><center><em>10.74</em></center></td><td><center><em>19.75</em></center></td><td><center><em>-</em></center></td><td><center><em>-</em></center></td><td><center><em>73.53</em></center></td><td><center><em>74.93</em></center></td><td><center><em>-</em></center></td><td><center><em>-</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>
<tr>
<td>RoLlama3.1-8b-Instruct-DPO-2025-04-23</td><td><center>9.22</center></td><td><center>22.75</center></td><td><center>-</center></td><td><center>-</center></td><td><center>30.82</center></td><td><center>20.25</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>RoLlama3.1-8b-Instruct-2024-10-09</td><td><center>5.42</center></td><td><center>5.95</center></td><td><center>4.89</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3.1-8b-Instruct-2025-04-23</em></td><td><center><em>6.43</em></center></td><td><center><em>6.78</em></center></td><td><center><em>6.09</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>6.21</center></td><td><center>6.74</center></td><td><center>5.69</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td>RoLlama3.1-8b-Instruct-DPO-2025-04-23</td><td><center><strong>7.00</strong></center></td><td><center><strong>7.30</strong></center></td><td><center><strong>6.70</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>RoLlama3.1-8b-Instruct-2024-10-09</td><td><center>3.55</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td><em>RoLlama3.1-8b-Instruct-2025-04-23</em></td><td><center><em>4.28</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>4.42</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td>RoLlama3.1-8b-Instruct-DPO-2025-04-23</td><td><center><strong>4.73</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-2025-04-23*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23) |
|RoLlama3.1-8b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO-2024-10-09) |
|RoLlama3.1-8b-Instruct-DPO-2025-04-23| [link](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO-2025-04-23) |
## Citation
```
@inproceedings{masala-etal-2024-vorbesti,
title = "``Vorbe\c{s}ti Rom{\^a}ne\c{s}te?'' A Recipe to Train Powerful {R}omanian {LLM}s with {E}nglish Instructions",
author = "Masala, Mihai and Ilie-Ablachim, Denis and Dima, Alexandru and Corlatescu, Dragos Georgian and Zavelca, Miruna-Andreea and Olaru, Ovio and Terian, Simina-Maria and Terian, Andrei and Leordeanu, Marius and Velicu, Horia and Popescu, Marius and Dascalu, Mihai and Rebedea, Traian",
editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.681/",
doi = "10.18653/v1/2024.findings-emnlp.681",
pages = "11632--11647"
}
```
<!-- **APA:**
[More Information Needed] -->
Reference in New Issue Copy Permalink