Hugging Face's logo

OpenLLM-Ro
/
RoGemma-7b-Instruct-2024-06-28

Text Generation
Transformers
Safetensors
Romanian
gemma
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
RoGemma-7b-Instruct-2024-06-28 / README.md
mihaimasala's picture
mihaimasala
Update README.md
6047b0a verified
preview code
|
raw
history blame contribute delete
25.6 kB
---
license: cc-by-nc-4.0
language:
- ro
base_model:
- google/gemma-7b
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/RoGemma-7b-Instruct-2024-06-28
results:
- task:
type: text-generation
dataset:
name: RoMT-Bench
type: RoMT-Bench
metrics:
- name: Score
type: Score
value: 5.26
- task:
type: text-generation
dataset:
name: RoCulturaBench
type: RoCulturaBench
metrics:
- name: Score
type: Score
value: 3.26
- task:
type: text-generation
dataset:
name: Romanian_Academic_Benchmarks
type: Romanian_Academic_Benchmarks
metrics:
- name: Average accuracy
type: accuracy
value: 53.41
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_arc_challenge
type: OpenLLM-Ro/ro_arc_challenge
metrics:
- name: Average accuracy
type: accuracy
value: 52.44
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_mmlu
type: OpenLLM-Ro/ro_mmlu
metrics:
- name: Average accuracy
type: accuracy
value: 54.44
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_winogrande
type: OpenLLM-Ro/ro_winogrande
metrics:
- name: Average accuracy
type: accuracy
value: 69.36
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_hellaswag
type: OpenLLM-Ro/ro_hellaswag
metrics:
- name: Average accuracy
type: accuracy
value: 61.96
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_gsm8k
type: OpenLLM-Ro/ro_gsm8k
metrics:
- name: Average accuracy
type: accuracy
value: 31.06
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_truthfulqa
type: OpenLLM-Ro/ro_truthfulqa
metrics:
- name: Average accuracy
type: accuracy
value: 51.23
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary
type: LaRoSeDa_binary
metrics:
- name: Average macro-f1
type: macro-f1
value: 97.86
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass
type: LaRoSeDa_multiclass
metrics:
- name: Average macro-f1
type: macro-f1
value: 65.70
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary_finetuned
type: LaRoSeDa_binary_finetuned
metrics:
- name: Average macro-f1
type: macro-f1
value: 98.43
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass_finetuned
type: LaRoSeDa_multiclass_finetuned
metrics:
- name: Average macro-f1
type: macro-f1
value: 87.17
- task:
type: text-generation
dataset:
name: WMT_EN-RO
type: WMT_EN-RO
metrics:
- name: Average bleu
type: bleu
value: 27.91
- task:
type: text-generation
dataset:
name: WMT_RO-EN
type: WMT_RO-EN
metrics:
- name: Average bleu
type: bleu
value: 23.08
- task:
type: text-generation
dataset:
name: WMT_EN-RO_finetuned
type: WMT_EN-RO_finetuned
metrics:
- name: Average bleu
type: bleu
value: 27.99
- task:
type: text-generation
dataset:
name: WMT_RO-EN_finetuned
type: WMT_RO-EN_finetuned
metrics:
- name: Average bleu
type: bleu
value: 39.51
- task:
type: text-generation
dataset:
name: XQuAD
type: XQuAD
metrics:
- name: Average exact_match
type: exact_match
value: 17.75
- task:
type: text-generation
dataset:
name: XQuAD
type: XQuAD
metrics:
- name: Average f1
type: f1
value: 28.11
- task:
type: text-generation
dataset:
name: XQuAD_finetuned
type: XQuAD_finetuned
metrics:
- name: Average exact_match
type: exact_match
value: 52.02
- task:
type: text-generation
dataset:
name: XQuAD_finetuned
type: XQuAD_finetuned
metrics:
- name: Average f1
type: f1
value: 68.43
- task:
type: text-generation
dataset:
name: STS
type: STS
metrics:
- name: Average spearman
type: spearman
value: 73.96
- task:
type: text-generation
dataset:
name: STS
type: STS
metrics:
- name: Average pearson
type: pearson
value: 75.16
- task:
type: text-generation
dataset:
name: STS_finetuned
type: STS_finetuned
metrics:
- name: Average spearman
type: spearman
value: 86.45
- task:
type: text-generation
dataset:
name: STS_finetuned
type: STS_finetuned
metrics:
- name: Average pearson
type: pearson
value: 86.31
- task:
type: text-generation
dataset:
name: RoMT-Bench
type: RoMT-Bench
metrics:
- name: First turn
type: Score
value: 5.92
- name: Second turn
type: Score
value: 4.60
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_arc_challenge
type: OpenLLM-Ro/ro_arc_challenge
metrics:
- name: 0-shot
type: accuracy
value: 50.30
- name: 1-shot
type: accuracy
value: 50.90
- name: 3-shot
type: accuracy
value: 52.53
- name: 5-shot
type: accuracy
value: 53.30
- name: 10-shot
type: accuracy
value: 54.33
- name: 25-shot
type: accuracy
value: 53.30
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_mmlu
type: OpenLLM-Ro/ro_mmlu
metrics:
- name: 0-shot
type: accuracy
value: 54.95
- name: 1-shot
type: accuracy
value: 54.01
- name: 3-shot
type: accuracy
value: 54.03
- name: 5-shot
type: accuracy
value: 54.76
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_winogrande
type: OpenLLM-Ro/ro_winogrande
metrics:
- name: 0-shot
type: accuracy
value: 68.67
- name: 1-shot
type: accuracy
value: 69.46
- name: 3-shot
type: accuracy
value: 68.43
- name: 5-shot
type: accuracy
value: 70.88
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_hellaswag
type: OpenLLM-Ro/ro_hellaswag
metrics:
- name: 0-shot
type: accuracy
value: 61.54
- name: 1-shot
type: accuracy
value: 61.54
- name: 3-shot
type: accuracy
value: 62.08
- name: 5-shot
type: accuracy
value: 62.12
- name: 10-shot
type: accuracy
value: 62.51
- task:
type: text-generation
dataset:
name: OpenLLM-Ro/ro_gsm8k
type: OpenLLM-Ro/ro_gsm8k
metrics:
- name: 1-shot
type: accuracy
value: 24.79
- name: 3-shot
type: accuracy
value: 34.50
- name: 5-shot
type: accuracy
value: 33.89
- task:
type: text-generation
dataset:
name: LaRoSeDa_binary
type: LaRoSeDa_binary
metrics:
- name: 0-shot
type: macro-f1
value: 97.60
- name: 1-shot
type: macro-f1
value: 97.23
- name: 3-shot
type: macro-f1
value: 98.13
- name: 5-shot
type: macro-f1
value: 98.50
- task:
type: text-generation
dataset:
name: LaRoSeDa_multiclass
type: LaRoSeDa_multiclass
metrics:
- name: 0-shot
type: macro-f1
value: 68.53
- name: 1-shot
type: macro-f1
value: 64.84
- name: 3-shot
type: macro-f1
value: 63.62
- name: 5-shot
type: macro-f1
value: 65.83
- task:
type: text-generation
dataset:
name: WMT_EN-RO
type: WMT_EN-RO
metrics:
- name: 0-shot
type: bleu
value: 25.04
- name: 1-shot
type: bleu
value: 28.43
- name: 3-shot
type: bleu
value: 28.87
- name: 5-shot
type: bleu
value: 29.28
- task:
type: text-generation
dataset:
name: WMT_RO-EN
type: WMT_RO-EN
metrics:
- name: 0-shot
type: bleu
value: 4.94
- name: 1-shot
type: bleu
value: 25.33
- name: 3-shot
type: bleu
value: 30.87
- name: 5-shot
type: bleu
value: 31.19
- task:
type: text-generation
dataset:
name: XQuAD_EM
type: XQuAD_EM
metrics:
- name: 0-shot
type: exact_match
value: 36.47
- name: 1-shot
type: exact_match
value: 26.22
- name: 3-shot
type: exact_match
value: 3.19
- name: 5-shot
type: exact_match
value: 5.13
- task:
type: text-generation
dataset:
name: XQuAD_F1
type: XQuAD_F1
metrics:
- name: 0-shot
type: f1
value: 56.83
- name: 1-shot
type: f1
value: 38.53
- name: 3-shot
type: f1
value: 6.88
- name: 5-shot
type: f1
value: 10.19
- task:
type: text-generation
dataset:
name: STS_Spearman
type: STS_Spearman
metrics:
- name: 1-shot
type: spearman
value: 70.61
- name: 3-shot
type: spearman
value: 73.53
- name: 5-shot
type: spearman
value: 77.73
- task:
type: text-generation
dataset:
name: STS_Pearson
type: STS_Pearson
metrics:
- name: 1-shot
type: pearson
value: 72.28
- name: 3-shot
type: pearson
value: 74.46
- name: 5-shot
type: pearson
value: 78.75
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
RoGemma 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-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:** [gemma-7b](https://huggingface.co/google/gemma-7b)
- **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-Factory
- **Paper:** https://arxiv.org/abs/2406.18266
## Intended Use
### Intended Use Cases
RoGemma 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/RoGemma-7b-Instruct-2024-06-28")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoGemma-7b-Instruct-2024-06-28")
instruction = "Ce jocuri de societate pot juca cu prietenii mei?"
chat = [
{"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>gemma-1.1-7b-it</td><td><center>41.44</center></td><td><center>40.32</center></td><td><center>47.22</center></td><td><center>55.01</center></td><td><center>47.03</center></td><td><center>9.50</center></td><td><center>49.58</center></td>
</tr>
<tr>
<td><em>RoGemma-7b-Instruct-2024-06-28</em></td><td><center><em><strong>53.41</strong></em></center></td><td><center><em><strong>52.44</strong></em></center></td><td><center><em>54.44</em></center></td><td><center><em><strong>69.36</strong></em></center></td><td><center><em><strong>61.96</strong></em></center></td><td><center><em>31.06</em></center></td><td><center><em><strong>51.23</strong></em></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-2024-10-09</td><td><center>50.48</center></td><td><center>52.01</center></td><td><center>52.37</center></td><td><center>66.97</center></td><td><center>56.34</center></td><td><center>25.98</center></td><td><center>49.18</center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-DPO-2024-10-09</td><td><center>48.27</center></td><td><center>46.66</center></td><td><center><strong>54.45</strong></center></td><td><center>63.73</center></td><td><center>49.33</center></td><td><center><strong>34.98</strong></center></td><td><center>40.45</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>gemma-1.1-7b-it</td><td><center>87.54</center></td><td><center>51.48</center></td><td><center>83.87</center></td><td><center>85.61</center></td><td><center>17.96</center></td><td><center><strong>27.74</strong></center></td><td><center>25.48</center></td><td><center>36.11</center></td>
</tr>
<tr>
<td><em>RoGemma-7b-Instruct-2024-06-28</em></td><td><center><em><strong>97.86</strong></em></center></td><td><center><em><strong>65.70</strong></em></center></td><td><center><em>98.43</em></center></td><td><center><em><strong>87.17</strong></em></center></td><td><center><em><strong>27.91</strong></em></center></td><td><center><em>23.08</em></center></td><td><center><em><strong>27.99</strong></em></center></td><td><center><em><strong>39.51</strong></em></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-2024-10-09</td><td><center>86.96</center></td><td><center>56.72</center></td><td><center><strong>98.80</strong></center></td><td><center>85.81</center></td><td><center>24.45</center></td><td><center>14.20</center></td><td><center>25.96</center></td><td><center>39.07</center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-DPO-2024-10-09</td><td><center>96.45</center></td><td><center>63.23</center></td><td><center>-</center></td><td><center>-</center></td><td><center>20.73</center></td><td><center>7.87</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>gemma-1.1-7b-it</td><td><center><strong>42.10</strong></center></td><td><center><strong>62.30</strong></center></td><td><center><strong>60.34</strong></center></td><td><center><strong>77.40</strong></center></td><td><center>49.10</center></td><td><center>50.23</center></td><td><center>83.43</center></td><td><center>83.64</center></td>
</tr>
<tr>
<td><em>RoGemma-7b-Instruct-2024-06-28</em></td><td><center><em>17.75</em></center></td><td><center><em>28.11</em></center></td><td><center><em>52.02</em></center></td><td><center><em>68.43</em></center></td><td><center><em><strong>73.96</strong></em></center></td><td><center><em><strong>75.16</strong></em></center></td><td><center><em>86.45</em></center></td><td><center><em>86.31</em></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-2024-10-09</td><td><center>26.03</center></td><td><center>41.58</center></td><td><center>46.72</center></td><td><center>60.79</center></td><td><center>73.23</center></td><td><center>71.58</center></td><td><center><strong>88.42</strong></center></td><td><center><strong>88.45</strong></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-DPO-2024-10-09</td><td><center>19.14</center></td><td><center>38.10</center></td><td><center>-</center></td><td><center>-</center></td><td><center>69.38</center></td><td><center>69.34</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>gemma-1.1-7b-it</td><td><center>4.83</center></td><td><center>5.11</center></td><td><center>4.55</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td><em>RoGemma-7b-Instruct-2024-06-28</em></td><td><center><em>5.26</em></center></td><td><center><em><strong>5.92</strong></em></center></td><td><center><em>4.60</em></center></td><td><center><em><strong>160/160</strong></em></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-2024-10-09</td><td><center>5.24</center></td><td><center>5.55</center></td><td><center>4.94</center></td><td><center><strong>160/160</strong></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-DPO-2024-10-09</td><td><center><strong>5.47</strong></center></td><td><center><strong>5.92</strong></center></td><td><center><strong>5.03</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>gemma-1.1-7b-it</td><td><center>3.38</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td><em>RoGemma-7b-Instruct-2024-06-28</em></td><td><center><em>3.26</em></center></td><td><center><em><strong>100/100</strong></em></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-2024-10-09</td><td><center>3.51</center></td><td><center><strong>100/100</strong></center></td>
</tr>
<tr>
<td>RoGemma-7b-Instruct-DPO-2024-10-09</td><td><center><strong>3.94</strong></center></td><td><center><strong>100/100</strong></center></td>
</tr>
</tbody>
</table>
## RoGemma Model Family
| Model | Link |
|--------------------|:--------:|
|*RoGemma-7b-Instruct-2024-06-28*| [link](https://huggingface.co/OpenLLM-Ro/RoGemma-7b-Instruct-2024-06-28) |
|RoGemma-7b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoGemma-7b-Instruct-2024-10-09) |
|RoGemma-7b-Instruct-DPO-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoGemma-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] -->