--- license: llama2 language: - ro base_model: meta-llama/Llama-2-7b-hf model-index: - name: OpenLLM-Ro/RoLlama2-7b-Base results: - task: type: text-generation dataset: name: Romanian_Academic_Benchmarks type: Romanian_Academic_Benchmarks metrics: - name: Average type: accuracy value: 38.033944444444444 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_arc_challenge type: OpenLLM-Ro/ro_arc_challenge metrics: - name: Average type: accuracy value: 37.945 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_mmlu type: OpenLLM-Ro/ro_mmlu metrics: - name: Average type: accuracy value: 27.2175 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_winogrande type: OpenLLM-Ro/ro_winogrande metrics: - name: Average type: accuracy value: 59.2925 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_hellaswag type: OpenLLM-Ro/ro_hellaswag metrics: - name: Average type: accuracy value: 57.222 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_gsm8k type: OpenLLM-Ro/ro_gsm8k metrics: - name: Average type: accuracy value: 2.526666666666667 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_truthfulqa type: OpenLLM-Ro/ro_truthfulqa metrics: - name: Average type: accuracy value: 44.0 - task: type: text-generation dataset: name: LaRoSeDa_binary type: LaRoSeDa_binary metrics: - name: Average type: macro-f1 value: 83.245 - task: type: text-generation dataset: name: LaRoSeDa_multiclass type: LaRoSeDa_multiclass metrics: - name: Average type: macro-f1 value: 61.040000000000006 - task: type: text-generation dataset: name: LaRoSeDa_binary_finetuned type: LaRoSeDa_binary_finetuned metrics: - name: Average type: macro-f1 value: 98.9666527738873 - task: type: text-generation dataset: name: LaRoSeDa_multiclass_finetuned type: LaRoSeDa_multiclass_finetuned metrics: - name: Average type: macro-f1 value: 87.7198050161592 - task: type: text-generation dataset: name: WMT_EN-RO type: WMT_EN-RO metrics: - name: Average type: bleu value: 10.01 - task: type: text-generation dataset: name: WMT_RO-EN type: WMT_RO-EN metrics: - name: Average type: bleu value: 13.032499999999999 - task: type: text-generation dataset: name: WMT_EN-RO_finetuned type: WMT_EN-RO_finetuned metrics: - name: Average type: bleu value: 27.8468226696502 - task: type: text-generation dataset: name: WMT_RO-EN_finetuned type: WMT_RO-EN_finetuned metrics: - name: Average type: bleu value: 39.300054525566104 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average type: exact_match value: 30.14705 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average type: f1 value: 47.0304 - task: type: text-generation dataset: name: XQuAD_finetuned type: XQuAD_finetuned metrics: - name: Average type: exact_match value: 67.0588235294117 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average type: f1 value: 79.9624140326139 - task: type: text-generation dataset: name: STS type: STS metrics: - name: Average type: spearman value: 7.886666666666667 - task: type: text-generation dataset: name: STS type: STS metrics: - name: Average type: pearson value: 7.976666666666667 - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - name: Average type: spearman value: 71.749068976055 - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - name: Average type: pearson value: 71.9866084841066 --- # Model Card for Model ID 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 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 - **Language(s):** Romanian - **License:** Llama2 Community License Agreement - **Continual pretrained from model:** [Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b-hf) ### Model Sources - **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 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 | Model | Average | ARC | MMLU |Winogrande|HellaSwag | GSM8k |TruthfulQA| |--------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| | Llama-2-7b | 37.04 | 36.05 | **33.66** | 57.56 | 48.00 | **4.75** | 42.22 | | *RoLlama2-7b-Base* | ***38.03*** | ***37.95*** | *27.22* | ***59.29*** | ***57.22*** | *2.53* | ***44.00*** | ## RoLlama2 Model Family | Model | Link | |--------------------|:--------:| |*RoLlama2-7b-Base* | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base) | |RoLlama2-7b-Instruct| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct) | |RoLlama2-7b-Chat | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Chat) | ## 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}, } ```