--- 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 - OpenLLM-Ro/ro_sft_oasst - OpenLLM-Ro/ro_sft_ultrachat model-index: - name: OpenLLM-Ro/RoGemma-7b-Instruct-2024-10-09 results: - task: type: text-generation dataset: name: RoMT-Bench type: RoMT-Bench metrics: - name: Score type: Score value: 5.24 - task: type: text-generation dataset: name: RoCulturaBench type: RoCulturaBench metrics: - name: Score type: Score value: 3.51 - task: type: text-generation dataset: name: Romanian_Academic_Benchmarks type: Romanian_Academic_Benchmarks metrics: - name: Average accuracy type: accuracy value: 50.48 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_arc_challenge type: OpenLLM-Ro/ro_arc_challenge metrics: - name: Average accuracy type: accuracy value: 52.01 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_mmlu type: OpenLLM-Ro/ro_mmlu metrics: - name: Average accuracy type: accuracy value: 52.37 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_winogrande type: OpenLLM-Ro/ro_winogrande metrics: - name: Average accuracy type: accuracy value: 66.97 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_hellaswag type: OpenLLM-Ro/ro_hellaswag metrics: - name: Average accuracy type: accuracy value: 56.34 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_gsm8k type: OpenLLM-Ro/ro_gsm8k metrics: - name: Average accuracy type: accuracy value: 25.98 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_truthfulqa type: OpenLLM-Ro/ro_truthfulqa metrics: - name: Average accuracy type: accuracy value: 49.18 - task: type: text-generation dataset: name: LaRoSeDa_binary type: LaRoSeDa_binary metrics: - name: Average macro-f1 type: macro-f1 value: 86.96 - task: type: text-generation dataset: name: LaRoSeDa_multiclass type: LaRoSeDa_multiclass metrics: - name: Average macro-f1 type: macro-f1 value: 56.72 - task: type: text-generation dataset: name: LaRoSeDa_binary_finetuned type: LaRoSeDa_binary_finetuned metrics: - name: Average macro-f1 type: macro-f1 value: 98.80 - task: type: text-generation dataset: name: LaRoSeDa_multiclass_finetuned type: LaRoSeDa_multiclass_finetuned metrics: - name: Average macro-f1 type: macro-f1 value: 85.81 - task: type: text-generation dataset: name: WMT_EN-RO type: WMT_EN-RO metrics: - name: Average bleu type: bleu value: 24.45 - task: type: text-generation dataset: name: WMT_RO-EN type: WMT_RO-EN metrics: - name: Average bleu type: bleu value: 14.20 - task: type: text-generation dataset: name: WMT_EN-RO_finetuned type: WMT_EN-RO_finetuned metrics: - name: Average bleu type: bleu value: 25.96 - task: type: text-generation dataset: name: WMT_RO-EN_finetuned type: WMT_RO-EN_finetuned metrics: - name: Average bleu type: bleu value: 39.07 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average exact_match type: exact_match value: 26.03 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average f1 type: f1 value: 41.58 - task: type: text-generation dataset: name: XQuAD_finetuned type: XQuAD_finetuned metrics: - name: Average exact_match type: exact_match value: 46.72 - task: type: text-generation dataset: name: XQuAD_finetuned type: XQuAD_finetuned metrics: - name: Average f1 type: f1 value: 60.79 - task: type: text-generation dataset: name: STS type: STS metrics: - name: Average spearman type: spearman value: 73.23 - task: type: text-generation dataset: name: STS type: STS metrics: - name: Average pearson type: pearson value: 71.58 - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - name: Average spearman type: spearman value: 88.42 - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - name: Average pearson type: pearson value: 88.45 - task: type: text-generation dataset: name: RoMT-Bench type: RoMT-Bench metrics: - name: First turn type: Score value: 5.55 - name: Second turn type: Score value: 4.94 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_arc_challenge type: OpenLLM-Ro/ro_arc_challenge metrics: - name: 0-shot type: accuracy value: 49.53 - name: 1-shot type: accuracy value: 52.53 - name: 3-shot type: accuracy value: 51.50 - name: 5-shot type: accuracy value: 53.56 - name: 10-shot type: accuracy value: 52.53 - name: 25-shot type: accuracy value: 52.44 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_mmlu type: OpenLLM-Ro/ro_mmlu metrics: - name: 0-shot type: accuracy value: 51.81 - name: 1-shot type: accuracy value: 52.45 - name: 3-shot type: accuracy value: 52.52 - name: 5-shot type: accuracy value: 52.70 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_winogrande type: OpenLLM-Ro/ro_winogrande metrics: - name: 0-shot type: accuracy value: 66.54 - name: 1-shot type: accuracy value: 66.69 - name: 3-shot type: accuracy value: 67.09 - name: 5-shot type: accuracy value: 67.56 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_hellaswag type: OpenLLM-Ro/ro_hellaswag metrics: - name: 0-shot type: accuracy value: 58.80 - name: 1-shot type: accuracy value: 57.04 - name: 3-shot type: accuracy value: 55.85 - name: 5-shot type: accuracy value: 54.15 - name: 10-shot type: accuracy value: 55.88 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_gsm8k type: OpenLLM-Ro/ro_gsm8k metrics: - name: 1-shot type: accuracy value: 22.06 - name: 3-shot type: accuracy value: 25.40 - name: 5-shot type: accuracy value: 30.48 - task: type: text-generation dataset: name: LaRoSeDa_binary type: LaRoSeDa_binary metrics: - name: 0-shot type: macro-f1 value: 87.28 - name: 1-shot type: macro-f1 value: 86.40 - name: 3-shot type: macro-f1 value: 87.95 - name: 5-shot type: macro-f1 value: 86.20 - task: type: text-generation dataset: name: LaRoSeDa_multiclass type: LaRoSeDa_multiclass metrics: - name: 0-shot type: macro-f1 value: 38.35 - name: 1-shot type: macro-f1 value: 63.86 - name: 3-shot type: macro-f1 value: 62.03 - name: 5-shot type: macro-f1 value: 62.62 - task: type: text-generation dataset: name: WMT_EN-RO type: WMT_EN-RO metrics: - name: 0-shot type: bleu value: 11.39 - name: 1-shot type: bleu value: 28.08 - name: 3-shot type: bleu value: 29.18 - name: 5-shot type: bleu value: 29.13 - task: type: text-generation dataset: name: WMT_RO-EN type: WMT_RO-EN metrics: - name: 0-shot type: bleu value: 1.92 - name: 1-shot type: bleu value: 9.39 - name: 3-shot type: bleu value: 21.81 - name: 5-shot type: bleu value: 23.66 - task: type: text-generation dataset: name: XQuAD_EM type: XQuAD_EM metrics: - name: 0-shot type: exact_match value: 32.77 - name: 1-shot type: exact_match value: 20.25 - name: 3-shot type: exact_match value: 18.49 - name: 5-shot type: exact_match value: 32.60 - task: type: text-generation dataset: name: XQuAD_F1 type: XQuAD_F1 metrics: - name: 0-shot type: f1 value: 47.98 - name: 1-shot type: f1 value: 34.92 - name: 3-shot type: f1 value: 33.27 - name: 5-shot type: f1 value: 50.14 - task: type: text-generation dataset: name: STS_Spearman type: STS_Spearman metrics: - name: 1-shot type: spearman value: 71.75 - name: 3-shot type: spearman value: 71.83 - name: 5-shot type: spearman value: 76.11 - task: type: text-generation dataset: name: STS_Pearson type: STS_Pearson metrics: - name: 1-shot type: pearson value: 69.97 - name: 3-shot type: pearson value: 69.87 - name: 5-shot type: pearson value: 74.89 --- # Model Card for Model ID This model points/is identical to [RoGemma-7b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoGemma-7b-Instruct-2024-10-09). 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), [RoOpenAssistant](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_oasst), [RoUltraChat](https://huggingface.co/datasets/OpenLLM-Ro/ro_sft_ultrachat) ### 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 | |||||||
gemma-1.1-7b-it | |||||||
RoGemma-7b-Instruct-2024-06-28 | |||||||
RoGemma-7b-Instruct-2024-10-09 | |||||||
RoGemma-7b-Instruct-DPO-2024-10-09 |
Model | (Macro F1) |
(Macro F1) |
(Macro F1) |
(Macro F1) |
(Bleu) |
(Bleu) |
(Bleu) |
(Bleu) |
gemma-1.1-7b-it | ||||||||
RoGemma-7b-Instruct-2024-06-28 | ||||||||
RoGemma-7b-Instruct-2024-10-09 | ||||||||
RoGemma-7b-Instruct-DPO-2024-10-09 |
Model | ||||||||
gemma-1.1-7b-it | ||||||||
RoGemma-7b-Instruct-2024-06-28 | ||||||||
RoGemma-7b-Instruct-2024-10-09 | ||||||||
RoGemma-7b-Instruct-DPO-2024-10-09 |
Model | ||||
gemma-1.1-7b-it | ||||
RoGemma-7b-Instruct-2024-06-28 | ||||
RoGemma-7b-Instruct-2024-10-09 | ||||
RoGemma-7b-Instruct-DPO-2024-10-09 |
Model | ||
gemma-1.1-7b-it | ||
RoGemma-7b-Instruct-2024-06-28 | ||
RoGemma-7b-Instruct-2024-10-09 | ||
RoGemma-7b-Instruct-DPO-2024-10-09 |