|
--- |
|
license: llama2 |
|
language: |
|
- lt |
|
datasets: |
|
- uonlp/CulturaX |
|
--- |
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
Lt-Llama2 is a family of pretrained and fine-tuned generative text models for Lithuanian. 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 |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
Neurotechnology company marks the first open-source initiative dedicated to developing a large language model (LLM) specialized in Lithuanian. The company has created and publicly released a collection of Lithuanian LLMs, available both as foundational models and instructional variants. |
|
|
|
|
|
- **Developed by:** Neurotechnology |
|
<!-- - **Funded by [optional]:** [More Information Needed] --> |
|
<!-- - **Shared by [optional]:** [More Information Needed] --> |
|
<!-- - **Model type:** [More Information Needed] --> |
|
- **Language(s):** Lithuanian |
|
- **License:** Llama2 Community License Agreement |
|
- **Continual pretrained from model:** [Llama-2-13b](https://huggingface.co/meta-llama/Llama-2-13b-hf) |
|
|
|
### Model Sources |
|
|
|
<!-- Provide the basic links for the model. --> |
|
|
|
- **Paper:** https://arxiv.org/abs/2408.12963 |
|
|
|
## Intended Use |
|
|
|
### Intended Use Cases |
|
|
|
Lt-Llama2 is designed for research purposes in Lithuanian. The base models can be tailored for various natural language tasks, while the instruction models are geared towards assistant-like conversational interactions. |
|
|
|
### Prohibited use |
|
|
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> |
|
|
|
Utilizing the model in ways that breach the license, violate any applicable laws or regulations, or involve languages other than Lithuanian. |
|
|
|
|
|
|
|
## 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("neurotechnology/Lt-Llama-2-13b-hf") |
|
model = AutoModelForCausalLM.from_pretrained("neurotechnology/Lt-Llama-2-13b-hf") |
|
input_text = "Kartą gyveno senelis ir senelė " |
|
input_ids = tokenizer(input_text, return_tensors="pt") |
|
outputs = model.generate(**input_ids, max_new_tokens=100) |
|
print(tokenizer.decode(outputs[0])) |
|
``` |
|
|
|
## Benchmarks |
|
|
|
| Model | Average | ARC | MMLU |Winogrande|HellaSwag | GSM8k |TruthfulQA| |
|
|--------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:| |
|
| Llama-2-13b | 30.53 | 28.66 | **31.34** | 50.90 | 28.91 | **5.91** | **37.48** | |
|
| *Llama2-13b-Base* | ***36.42*** | ***54.50*** | *26.01* | ***61.72*** | ***40.61*** | *0.45* | *35.23* | |
|
|
|
|
|
|
|
## RoLlama2 Model Family |
|
|
|
| Model | Link | |
|
|--------------------|:--------:| |
|
|Lt-Llama2-7b | [link](https://huggingface.co/neurotechnology/Lt-Llama-2-7b-hf) | |
|
|Lt-Llama2-7b-instruct| [link](https://huggingface.co/neurotechnology/Lt-Llama-2-7b-instruct-hf) | |
|
|*Lt-Llama2-13b* | [link](https://huggingface.co/neurotechnology/Lt-Llama-2-13b-hf) | |
|
|Lt-Llama2-13b-instruct| [link](https://huggingface.co/neurotechnology/Lt-Llama-2-13b-instruct-hf) | |
|
|
|
|
|
## Citation |
|
|
|
```bibtext |
|
@misc{nakvosas2024openllama2modellithuanian, |
|
title={Open Llama2 Model for the Lithuanian Language}, |
|
author={Artūras Nakvosas and Povilas Daniušis and Vytas Mulevičius}, |
|
year={2024}, |
|
eprint={2408.12963}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CL}, |
|
url={https://arxiv.org/abs/2408.12963}, |
|
} |
|
``` |
|
|
|
<!-- **APA:** |
|
|
|
[More Information Needed] --> |
