---
license: cc-by-nc-4.0
language:
- ro
base_model:
- google/gemma-7b
---
# Model Card for Model ID
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
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
- **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
- **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
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")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoGemma-7b-Instruct")
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
| Model |
Average |
ARC |
MMLU |
Winogrande |
Hellaswag |
GSM8k |
TruthfulQA |
| gemma-1.1-7b-it | 41.44 | 40.32 | 47.22 | 55.01 | 47.03 | 9.50 | 49.58 |
| RoGemma-7b-Instruct | 53.42 | 52.44 | 54.44 | 69.36 | 61.96 | 31.06 | 51.23 |
## Downstream tasks
|
LaRoSeDa |
WMT |
|
Few-shot |
Finetuned |
Few-shot |
Finetuned |
| Model |
Binary
(Macro F1) |
Multiclass
(Macro F1) |
Binary
(Macro F1) |
Multiclass
(Macro F1) |
EN-RO
(Bleu) |
RO-EN
(Bleu) |
EN-RO
(Bleu) |
RO-EN
(Bleu)
|
| gemma-1.1-7b-it | 87.54 | 51.49 | 83.87 | 85.61 | 17.96 | 27.74 | 25.48 | 36.11 |
| RoGemma-7b-Instruct | 97.87 | 65.71 | 98.43 | 87.18 | 27.91 | 23.08 | 27.99 | 39.51 |
|
XQuAD |
STS |
|
Few-shot |
Finetuned |
Few-shot |
Finetuned |
| Model |
(EM) |
(F1) |
(EM) |
(F1) |
(Spearman) |
(Pearson) |
(Spearman) |
(Pearson) |
| gemma-1.1-7b-it | 42.10 | 62.30 | 60.34 | 77.40 | 49.10 | 50.23 | 83.43 | 83.65 |
| RoGemma-7b-Instruct | 17.75 | 28.11 | 52.02 | 68.43 | 73.96 | 75.16 | 86.45 | 86.31 |
## MT-Bench
| Model |
Average |
1st turn |
2nd turn |
Answers in Ro |
| gemma-1.1-7b-it | 4.83 | 5.11 | 4.55 | 160/160 |
| RoGemma-7b-Instruct | 5.26 | 5.92 | 4.60 | 160/160 |
## RoCulturaBench
| Model |
Average |
Answers in Ro |
| gemma-1.1-7b-it | 3.38 | 100/100 |
| RoGemma-7b-Instruct | 3.26 | 100/100 |
## RoGemma Model Family
| Model | Link |
|--------------------|:--------:|
|*RoGemma-7b-Instruct*| [link](https://huggingface.co/OpenLLM-Ro/RoGemma-7b-Instruct) |
## 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},
}
```