OpenLLM-Ro/RoLlama2-7b-Instruct

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 instruct 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: cc-by-nc-4.0
• Finetuned from model: RoLlama2-7b-Base

Model Sources

• Repository: https://github.com/OpenLLM-Ro/llama-recipes
• Paper: https://arxiv.org/abs/2405.07703

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.

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct")

instruction = "Care este cel mai înalt vârf muntos din România?"
chat = [
        {"role": "system", "content": "Ești un asistent folositor, respectuos și onest. Încearcă să ajuți cât mai mult prin informațiile oferite, excluzând răspunsuri toxice, rasiste, sexiste, periculoase și ilegale."},
        {"role": "user", "content": instruction},
        ]
prompt = tokenizer.apply_chat_template(chat, tokenize=False)

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]))

Benchmarks

Model	Average	ARC	MMLU	Winogrande	HellaSwag	GSM8k	TruthfulQA
Llama-2-7b	35.65	33.85	30.93	56.43	46.98	1.37	44.36
RoLlama2-7b-Base	38.32	35.83	30.47	60.16	55.52	2.17	45.78
Llama-2-7b-chat	35.58	34.92	32.37	54.26	44.52	2.05	45.38
RoLlama2-7b-Instruct	44.42	40.36	37.41	69.58	55.64	17.59	45.96
RoLlama2-7b-Chat	42.65	38.29	35.27	65.25	56.45	12.84	47.79

MT-Bench

Model	Average	1st turn	2nd turn
Llama-2-7b-chat	1.70	2.00	1.41
RoLlama2-7b-Instruct	4.31	5.66	2.95
RoLlama2-7b-Chat	3.91	4.25	3.57

RoLlama2 Model Family

Model	Link
RoLlama2-7b-Base	link
RoLlama2-7b-Instruct	link
RoLlama2-7b-Chat	link