--- license: cc-by-nc-4.0 language: - ro base_model: - OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09 datasets: - OpenLLM-Ro/ro_dpo_helpsteer model-index: - name: OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2024-10-09 results: - task: type: text-generation dataset: name: RoMT-Bench type: RoMT-Bench metrics: - name: Score type: Score value: 5.88 - task: type: text-generation dataset: name: RoCulturaBench type: RoCulturaBench metrics: - name: Score type: Score value: 4.72 - task: type: text-generation dataset: name: Romanian_Academic_Benchmarks type: Romanian_Academic_Benchmarks metrics: - name: Average accuracy type: accuracy value: 51.95 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_arc_challenge type: OpenLLM-Ro/ro_arc_challenge metrics: - name: Average accuracy type: accuracy value: 50.73 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_mmlu type: OpenLLM-Ro/ro_mmlu metrics: - name: Average accuracy type: accuracy value: 47.88 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_winogrande type: OpenLLM-Ro/ro_winogrande metrics: - name: Average accuracy type: accuracy value: 68.41 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_hellaswag type: OpenLLM-Ro/ro_hellaswag metrics: - name: Average accuracy type: accuracy value: 62.27 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_gsm8k type: OpenLLM-Ro/ro_gsm8k metrics: - name: Average accuracy type: accuracy value: 32.27 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_truthfulqa type: OpenLLM-Ro/ro_truthfulqa metrics: - name: Average accuracy type: accuracy value: 50.12 - task: type: text-generation dataset: name: LaRoSeDa_binary type: LaRoSeDa_binary metrics: - name: Average macro-f1 type: macro-f1 value: 82.13 - task: type: text-generation dataset: name: LaRoSeDa_multiclass type: LaRoSeDa_multiclass metrics: - name: Average macro-f1 type: macro-f1 value: 65.24 - task: type: text-generation dataset: name: LaRoSeDa_binary_finetuned type: LaRoSeDa_binary_finetuned metrics: - name: Average macro-f1 type: macro-f1 value: 0.00 - task: type: text-generation dataset: name: LaRoSeDa_multiclass_finetuned type: LaRoSeDa_multiclass_finetuned metrics: - name: Average macro-f1 type: macro-f1 value: 0.00 - task: type: text-generation dataset: name: WMT_EN-RO type: WMT_EN-RO metrics: - name: Average bleu type: bleu value: 26.25 - task: type: text-generation dataset: name: WMT_RO-EN type: WMT_RO-EN metrics: - name: Average bleu type: bleu value: 6.09 - task: type: text-generation dataset: name: WMT_EN-RO_finetuned type: WMT_EN-RO_finetuned metrics: - name: Average bleu type: bleu value: 0.00 - task: type: text-generation dataset: name: WMT_RO-EN_finetuned type: WMT_RO-EN_finetuned metrics: - name: Average bleu type: bleu value: 0.00 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average exact_match type: exact_match value: 23.40 - task: type: text-generation dataset: name: XQuAD type: XQuAD metrics: - name: Average f1 type: f1 value: 45.80 - task: type: text-generation dataset: name: XQuAD_finetuned type: XQuAD_finetuned metrics: - name: Average exact_match type: exact_match value: 0.00 - task: type: text-generation dataset: name: XQuAD_finetuned type: XQuAD_finetuned metrics: - name: Average f1 type: f1 value: 0.00 - task: type: text-generation dataset: name: STS type: STS metrics: - name: Average spearman type: spearman value: 77.33 - task: type: text-generation dataset: name: STS type: STS metrics: - name: Average pearson type: pearson value: 76.60 - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - name: Average spearman type: spearman value: 0.00 - task: type: text-generation dataset: name: STS_finetuned type: STS_finetuned metrics: - name: Average pearson type: pearson value: 0.00 - task: type: text-generation dataset: name: RoMT-Bench type: RoMT-Bench metrics: - name: First turn type: Score value: 6.44 - name: Second turn type: Score value: 5.33 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_arc_challenge type: OpenLLM-Ro/ro_arc_challenge metrics: - name: 0-shot type: accuracy value: 51.67 - name: 1-shot type: accuracy value: 45.59 - name: 3-shot type: accuracy value: 48.24 - name: 5-shot type: accuracy value: 50.21 - name: 10-shot type: accuracy value: 54.07 - name: 25-shot type: accuracy value: 54.58 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_mmlu type: OpenLLM-Ro/ro_mmlu metrics: - name: 0-shot type: accuracy value: 40.86 - name: 1-shot type: accuracy value: 48.67 - name: 3-shot type: accuracy value: 51.26 - name: 5-shot type: accuracy value: 50.75 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_winogrande type: OpenLLM-Ro/ro_winogrande metrics: - name: 0-shot type: accuracy value: 64.80 - name: 1-shot type: accuracy value: 68.19 - name: 3-shot type: accuracy value: 70.09 - name: 5-shot type: accuracy value: 70.56 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_hellaswag type: OpenLLM-Ro/ro_hellaswag metrics: - name: 0-shot type: accuracy value: 61.96 - name: 1-shot type: accuracy value: 60.88 - name: 3-shot type: accuracy value: 61.86 - name: 5-shot type: accuracy value: 62.73 - name: 10-shot type: accuracy value: 63.93 - task: type: text-generation dataset: name: OpenLLM-Ro/ro_gsm8k type: OpenLLM-Ro/ro_gsm8k metrics: - name: 1-shot type: accuracy value: 23.28 - name: 3-shot type: accuracy value: 34.95 - name: 5-shot type: accuracy value: 38.59 - task: type: text-generation dataset: name: LaRoSeDa_binary type: LaRoSeDa_binary metrics: - name: 0-shot type: macro-f1 value: 34.36 - name: 1-shot type: macro-f1 value: 97.87 - name: 3-shot type: macro-f1 value: 98.40 - name: 5-shot type: macro-f1 value: 97.90 - task: type: text-generation dataset: name: LaRoSeDa_multiclass type: LaRoSeDa_multiclass metrics: - name: 0-shot type: macro-f1 value: 66.17 - name: 1-shot type: macro-f1 value: 65.93 - name: 3-shot type: macro-f1 value: 61.86 - name: 5-shot type: macro-f1 value: 66.99 - task: type: text-generation dataset: name: WMT_EN-RO type: WMT_EN-RO metrics: - name: 0-shot type: bleu value: 18.43 - name: 1-shot type: bleu value: 28.25 - name: 3-shot type: bleu value: 29.45 - name: 5-shot type: bleu value: 28.88 - task: type: text-generation dataset: name: WMT_RO-EN type: WMT_RO-EN metrics: - name: 0-shot type: bleu value: 2.80 - name: 1-shot type: bleu value: 2.90 - name: 3-shot type: bleu value: 6.63 - name: 5-shot type: bleu value: 12.04 - task: type: text-generation dataset: name: XQuAD_EM type: XQuAD_EM metrics: - name: 0-shot type: exact_match value: 5.04 - name: 1-shot type: exact_match value: 22.44 - name: 3-shot type: exact_match value: 30.42 - name: 5-shot type: exact_match value: 35.71 - task: type: text-generation dataset: name: XQuAD_F1 type: XQuAD_F1 metrics: - name: 0-shot type: f1 value: 23.36 - name: 1-shot type: f1 value: 44.63 - name: 3-shot type: f1 value: 54.78 - name: 5-shot type: f1 value: 60.43 - task: type: text-generation dataset: name: STS_Spearman type: STS_Spearman metrics: - name: 1-shot type: spearman value: 73.38 - name: 3-shot type: spearman value: 78.93 - name: 5-shot type: spearman value: 79.68 - task: type: text-generation dataset: name: STS_Pearson type: STS_Pearson metrics: - name: 1-shot type: pearson value: 73.93 - name: 3-shot type: pearson value: 77.69 - name: 5-shot type: pearson value: 78.17 --- # Model Card for Model ID This model points/is identical to [RoMistral-7b-Instruct-DPO-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-DPO-2024-10-09). RoMistral is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **human aligned 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:** [RoMistral-7b-Instruct-2024-10-09](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09) - **Trained using:** [RoHelpSteer](https://huggingface.co/datasets/OpenLLM-Ro/ro_dpo_helpsteer) ### Model Sources - **Repository:** https://github.com/OpenLLM-Ro/LLaMA-Factory - **Paper:** https://arxiv.org/abs/2406.18266 ## Intended Use ### Intended Use Cases RoMistral 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/RoMistral-7b-Instruct-DPO") model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct-DPO") 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
Mistral-7B-Instruct-v0.2
47.40
46.29
47.00
58.78
54.27
13.47
64.59
RoMistral-7b-Instruct-2024-05-17
52.54
50.41
51.61
66.48
60.27
34.19
52.30
RoMistral-7b-Instruct-2024-10-09
52.91
52.27
49.33
70.03
62.88
32.42
50.51
RoMistral-7b-Instruct-DPO-2024-10-09
51.95
50.73
47.88
68.41
62.27
32.27
50.12
## 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)
Mistral-7B-Instruct-v0.2
96.97
56.66
98.83
87.32
18.60
33.99
26.19
39.88
RoMistral-7b-Instruct-2024-05-17
97.36
67.55
98.80
88.28
27.93
13.21
28.72
40.86
RoMistral-7b-Instruct-2024-10-09
95.56
67.83
99.00
87.57
28.28
6.10
27.70
40.36
RoMistral-7b-Instruct-DPO-2024-10-09
82.13
65.24
-
-
26.25
6.09
-
-
XQuAD
STS
Few-shot
Finetuned
Few-shot
Finetuned
Model
(EM)
(F1)
(EM)
(F1)
(Spearman)
(Pearson)
(Spearman)
(Pearson)
Mistral-7B-Instruct-v0.2
27.92
50.71
65.46
79.73
62.62
60.86
84.92
85.44
RoMistral-7b-Instruct-2024-05-17
43.66
63.70
55.04
72.31
77.43
78.43
87.25
87.79
RoMistral-7b-Instruct-2024-10-09
41.09
63.21
47.56
62.69
78.47
77.24
87.28
87.88
RoMistral-7b-Instruct-DPO-2024-10-09
23.40
45.80
-
-
77.33
76.60
-
-
## MT-Bench
Model
Average
1st turn
2nd turn
Answers in Ro
Mistral-7B-Instruct-v0.2
5.03
5.05
5.00
154/160
RoMistral-7b-Instruct-2024-05-17
4.99
5.46
4.53
160/160
RoMistral-7b-Instruct-2024-10-09
5.29
5.86
4.72
160/160
RoMistral-7b-Instruct-DPO-2024-10-09
5.88
6.44
5.33
160/160
## RoCulturaBench
Model
Average
Answers in Ro
Mistral-7B-Instruct-v0.2
3.68
97/100
RoMistral-7b-Instruct-2024-05-17
3.38
100/100
RoMistral-7b-Instruct-2024-10-09
3.99
100/100
RoMistral-7b-Instruct-DPO-2024-10-09
4.72
100/100
## RoMistral Model Family | Model | Link | |--------------------|:--------:| |RoMistral-7b-Instruct-2024-05-17| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17) | |RoMistral-7b-Instruct-2024-10-09| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-7b-Instruct-2024-10-09) | |*RoMistral-7b-Instruct-DPO-2024-10-09*| [link](https://huggingface.co/OpenLLM-Ro/RoMistral-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}, } ```