README.md

---
base_model:
- meta-llama/Llama-3.1-8B-Instruct
license: llama3.1
language:
- gl
metrics:
- bleu
- rouge
model-index:
- name: Llama-3.1-8B-Instruct-Galician
  results:
  - task:
      type: text-generation
    dataset:
      name: alpaca_data_galician
      type: alpaca_data_galician
    metrics:
    - name: bleu
      type: bleu-4
      value: 23.13
    - name: rouge
      type: rouge-l
      value: 21.84
pipeline_tag: text-generation
library_name: transformers
widget:
  - text: "Onde está o concello de Frades?"
    output:
      text: Frades é un concello da provincia da Coruña, pertencente á comarca de Ordes. Está situado a 15 quilómetros de Santiago de Compostela.
---

# Llama-3.1-8B-Instruct-Galician

This model is a continued pretraining version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [CorpusNós](https://zenodo.org/records/11655219) dataset.

## Model Description

- **Developed by:** [UDC Information Retrieval Lab (IRLab)](https://huggingface.co/irlab-udc)
- **Language(s) (NLP):** Multilingual, adapted to Galician
- **License:** llama3.1
- **Finetuned from model:** [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
- **Repository:** [Adapting Large Language Models for Underrepresented Languages](https://gitlab.irlab.org/eliseo.bao/xovetic-llms-underrepresented-languages)
- **Paper:** _Coming soon_

## How to Get Started with the Model

```python
import transformers
import torch

model_id = "irlab-udc/Llama-3.1-8B-Instruct-Galician"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a conversational AI that always responds in Galician."},
    {"role": "user", "content": "Cal é a principal vantaxe de usar Scrum?"},
]

outputs = pipeline(messages, max_new_tokens=512)

print(outputs[0]["generated_text"][-1]["content"])
```

#### Training Hyperparameters

| Parameter                     | Value                                |
|--------------------------------|--------------------------------------|
| learning_rate                  | 0.0001                               |
| train_batch_size               | 32                                   |
| eval_batch_size                | 1                                    |
| seed                           | 42                                   |
| distributed_type               | multi-GPU                            |
| num_devices                    | 4                                    |
| gradient_accumulation_steps     | 2                                    |
| total_train_batch_size         | 256                                  |
| total_eval_batch_size          | 4                                    |
| optimizer                      | Adam with betas=(0.9, 0.999), epsilon=1e-08 |
| lr_scheduler_type              | cosine                               |
| lr_scheduler_warmup_ratio      | 0.1                                  |
| num_epochs                     | 1.0                                  |


#### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.0606        | 0.1682 | 900  | 2.0613          |
| 1.9898        | 0.3363 | 1800 | 1.9929          |
| 1.9847        | 0.5045 | 2700 | 1.9613          |
| 1.9577        | 0.6726 | 3600 | 1.9445          |
| 1.9287        | 0.8408 | 4500 | 1.9368          |

## Environmental Impact

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** 4x NVIDIA A100 SXM4 80 GB (TDP of 400W)
- **Hours used:** 60
- **Cloud Provider:** Private infrastructure
- **Carbon Emitted:** 10.37 Kg. CO₂ eq.

## Citation

_Coming soon_