Model Card for Model ID
RoMistral 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: Mistral-7B-v0.1
- Trained using: RoAlpaca, RoAlpacaGPT4, RoDolly, RoSelfInstruct, RoNoRobots, RoOrca, RoCamel
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.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct-05-17")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct-05-17")
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 | |||||||
Mistral-7B-Instruct-v0.2 | |||||||
RoMistral-7b-Instruct-2024-05-17 | |||||||
RoMistral-7b-Instruct-2024-10-09 | |||||||
RoMistral-7b-Instruct-DPO-2024-10-09 |
Downstream tasks
Model | (Macro F1) |
(Macro F1) |
(Macro F1) |
(Macro F1) |
(Bleu) |
(Bleu) |
(Bleu) |
(Bleu) |
Mistral-7B-Instruct-v0.2 | ||||||||
RoMistral-7b-Instruct-2024-05-17 | ||||||||
RoMistral-7b-Instruct-2024-10-09 | ||||||||
RoMistral-7b-Instruct-DPO-2024-10-09 |
Model | ||||||||
Mistral-7B-Instruct-v0.2 | ||||||||
RoMistral-7b-Instruct-2024-05-17 | ||||||||
RoMistral-7b-Instruct-2024-10-09 | ||||||||
RoMistral-7b-Instruct-DPO-2024-10-09 |
MT-Bench
Model | ||||
Mistral-7B-Instruct-v0.2 | ||||
RoMistral-7b-Instruct-2024-05-17 | ||||
RoMistral-7b-Instruct-2024-10-09 | ||||
RoMistral-7b-Instruct-DPO-2024-10-09 |
RoCulturaBench
Model | ||
Mistral-7B-Instruct-v0.2 | ||
RoMistral-7b-Instruct-2024-05-17 | ||
RoMistral-7b-Instruct-2024-10-09 | ||
RoMistral-7b-Instruct-DPO-2024-10-09 |
RoMistral Model Family
Model | Link |
---|---|
RoMistral-7b-Instruct-2024-05-17 | link |
RoMistral-7b-Instruct-2024-10-09 | link |
RoMistral-7b-Instruct-DPO-2024-10-09 | link |
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},
}
- Downloads last month
- 387
Model tree for OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17
Datasets used to train OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17
Collection including OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17
Evaluation results
- Score on RoMT-Benchself-reported4.990
- Score on RoCulturaBenchself-reported3.380
- Average accuracy on Romanian_Academic_Benchmarksself-reported52.540
- Average accuracy on OpenLLM-Ro/ro_arc_challengeself-reported50.410
- Average accuracy on OpenLLM-Ro/ro_mmluself-reported51.610
- Average accuracy on OpenLLM-Ro/ro_winograndeself-reported66.480
- Average accuracy on OpenLLM-Ro/ro_hellaswagself-reported60.270
- Average accuracy on OpenLLM-Ro/ro_gsm8kself-reported34.190
- Average accuracy on OpenLLM-Ro/ro_truthfulqaself-reported52.300
- Average macro-f1 on LaRoSeDa_binaryself-reported97.360