|
--- |
|
license: llama2 |
|
language: |
|
- ro |
|
base_model: meta-llama/Llama-2-7b-hf |
|
datasets: |
|
- uonlp/CulturaX |
|
model-index: |
|
- name: OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14 |
|
results: |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: Romanian_Academic_Benchmarks |
|
type: Romanian_Academic_Benchmarks |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 38.03 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 37.95 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 27.22 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 59.29 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 57.22 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 2.53 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_truthfulqa |
|
type: OpenLLM-Ro/ro_truthfulqa |
|
metrics: |
|
- name: Average accuracy |
|
type: accuracy |
|
value: 44.00 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary |
|
type: LaRoSeDa_binary |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 83.25 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 61.04 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary_finetuned |
|
type: LaRoSeDa_binary_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 98.97 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass_finetuned |
|
type: LaRoSeDa_multiclass_finetuned |
|
metrics: |
|
- name: Average macro-f1 |
|
type: macro-f1 |
|
value: 87.72 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 10.01 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 13.03 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO_finetuned |
|
type: WMT_EN-RO_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 27.85 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN_finetuned |
|
type: WMT_RO-EN_finetuned |
|
metrics: |
|
- name: Average bleu |
|
type: bleu |
|
value: 39.30 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 30.15 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD |
|
type: XQuAD |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 47.03 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average exact_match |
|
type: exact_match |
|
value: 67.06 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_finetuned |
|
type: XQuAD_finetuned |
|
metrics: |
|
- name: Average f1 |
|
type: f1 |
|
value: 79.96 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 7.89 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS |
|
type: STS |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 7.98 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average spearman |
|
type: spearman |
|
value: 71.75 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_finetuned |
|
type: STS_finetuned |
|
metrics: |
|
- name: Average pearson |
|
type: pearson |
|
value: 71.99 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_arc_challenge |
|
type: OpenLLM-Ro/ro_arc_challenge |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 35.56 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 36.42 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 38.56 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 38.39 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 39.07 |
|
- name: 25-shot |
|
type: accuracy |
|
value: 39.67 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_mmlu |
|
type: OpenLLM-Ro/ro_mmlu |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 25.82 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 25.48 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 27.61 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 29.96 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_winogrande |
|
type: OpenLLM-Ro/ro_winogrande |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 58.72 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 58.88 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 60.38 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 59.19 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_hellaswag |
|
type: OpenLLM-Ro/ro_hellaswag |
|
metrics: |
|
- name: 0-shot |
|
type: accuracy |
|
value: 55.85 |
|
- name: 1-shot |
|
type: accuracy |
|
value: 57.06 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 57.52 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 57.89 |
|
- name: 10-shot |
|
type: accuracy |
|
value: 57.79 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: OpenLLM-Ro/ro_gsm8k |
|
type: OpenLLM-Ro/ro_gsm8k |
|
metrics: |
|
- name: 1-shot |
|
type: accuracy |
|
value: 0.00 |
|
- name: 3-shot |
|
type: accuracy |
|
value: 2.96 |
|
- name: 5-shot |
|
type: accuracy |
|
value: 4.62 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_binary |
|
type: LaRoSeDa_binary |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 42.78 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 98.00 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 95.13 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 97.07 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: LaRoSeDa_multiclass |
|
type: LaRoSeDa_multiclass |
|
metrics: |
|
- name: 0-shot |
|
type: macro-f1 |
|
value: 46.41 |
|
- name: 1-shot |
|
type: macro-f1 |
|
value: 67.36 |
|
- name: 3-shot |
|
type: macro-f1 |
|
value: 65.16 |
|
- name: 5-shot |
|
type: macro-f1 |
|
value: 65.23 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_EN-RO |
|
type: WMT_EN-RO |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 4.45 |
|
- name: 1-shot |
|
type: bleu |
|
value: 8.61 |
|
- name: 3-shot |
|
type: bleu |
|
value: 12.25 |
|
- name: 5-shot |
|
type: bleu |
|
value: 14.73 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: WMT_RO-EN |
|
type: WMT_RO-EN |
|
metrics: |
|
- name: 0-shot |
|
type: bleu |
|
value: 1.29 |
|
- name: 1-shot |
|
type: bleu |
|
value: 10.78 |
|
- name: 3-shot |
|
type: bleu |
|
value: 16.82 |
|
- name: 5-shot |
|
type: bleu |
|
value: 23.24 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_EM |
|
type: XQuAD_EM |
|
metrics: |
|
- name: 0-shot |
|
type: exact_match |
|
value: 5.29 |
|
- name: 1-shot |
|
type: exact_match |
|
value: 33.95 |
|
- name: 3-shot |
|
type: exact_match |
|
value: 39.24 |
|
- name: 5-shot |
|
type: exact_match |
|
value: 42.10 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: XQuAD_F1 |
|
type: XQuAD_F1 |
|
metrics: |
|
- name: 0-shot |
|
type: f1 |
|
value: 16.17 |
|
- name: 1-shot |
|
type: f1 |
|
value: 51.84 |
|
- name: 3-shot |
|
type: f1 |
|
value: 58.82 |
|
- name: 5-shot |
|
type: f1 |
|
value: 61.29 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Spearman |
|
type: STS_Spearman |
|
metrics: |
|
- name: 1-shot |
|
type: spearman |
|
value: -1.74 |
|
- name: 3-shot |
|
type: spearman |
|
value: 15.47 |
|
- name: 5-shot |
|
type: spearman |
|
value: 9.93 |
|
- task: |
|
type: text-generation |
|
dataset: |
|
name: STS_Pearson |
|
type: STS_Pearson |
|
metrics: |
|
- name: 1-shot |
|
type: pearson |
|
value: -1.40 |
|
- name: 3-shot |
|
type: pearson |
|
value: 15.00 |
|
- name: 5-shot |
|
type: pearson |
|
value: 10.33 |
|
|
|
|
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
This model points/is identical to [RoLlama2-7b-Base-2024-05-14](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base-2024-05-14). |
|
|
|
RoLlama2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **foundational 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:** Llama2 Community License Agreement |
|
- **Continual pretrained from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) |
|
- **Trained using:** [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX) |
|
|
|
|
|
### 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-Base") |
|
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Base") |
|
|
|
input_text = "Mihai Eminescu a fost " |
|
input_ids = tokenizer(input_text, return_tensors="pt") |
|
|
|
outputs = model.generate(**input_ids, max_new_tokens=100) |
|
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</td><td><center>37.04</center></td><td><center>36.05</center></td><td><center><strong>33.66</strong></center></td><td><center>57.56</center></td><td><center>48.00</center></td><td><center><strong>4.75</strong></center></td><td><center>42.22</center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama2-7b-Base-2024-05-14</em></td><td><center><em><strong>38.03</strong></em></center></td><td><center><em><strong>37.95</strong></em></center></td><td><center><em>27.22</em></center></td><td><center><em><strong>59.29</strong></em></center></td><td><center><em><strong>57.22</strong></em></center></td><td><center><em>2.53</em></center></td><td><center><em><strong>44.00</strong></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-2-7b</td><td><center><strong>93.19</strong></center></td><td><center>54.11</center></td><td><center>98.43</center></td><td><center>87.22</center></td><td><center><strong>14.90</strong></center></td><td><center><strong>26.61</strong></center></td><td><center>24.95</center></td><td><center>39.09</center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama2-7b-Base-2024-05-14</em></td><td><center><em>83.25</em></center></td><td><center><em><strong>61.04</strong></em></center></td><td><center><em><strong>98.97</strong></em></center></td><td><center><em><strong>87.72</strong></em></center></td><td><center><em>10.01</em></center></td><td><center><em>13.03</em></center></td><td><center><em><strong>27.85</strong></em></center></td><td><center><em><strong>39.30</strong></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-2-7b</td><td><center><strong>38.91</strong></center></td><td><center><strong>56.82</strong></center></td><td><center>65.46</center></td><td><center>79.42</center></td><td><center><strong>9.08</strong></center></td><td><center><strong>9.07</strong></center></td><td><center><strong>79.93</strong></center></td><td><center><strong>81.08</strong></center></td> |
|
</tr> |
|
<tr> |
|
<td><em>RoLlama2-7b-Base-2024-05-14</em></td><td><center><em>30.15</em></center></td><td><center><em>47.03</em></center></td><td><center><em><strong>67.06</strong></em></center></td><td><center><em><strong>79.96</strong></em></center></td><td><center><em>7.89</em></center></td><td><center><em>7.98</em></center></td><td><center><em>71.75</em></center></td><td><center><em>71.99</em></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] --> |
