The Cabrita model is a collection of continued pre-trained and tokenizer-adapted models for the Portuguese language. This artifact is the 3 billion size variant.
The weights were initially obtained from the open-llama project (https://github.com/openlm-research/open_llama) in the open_llama_3b option.
@misc{larcher2023cabrita,
title={Cabrita: closing the gap for foreign languages},
author={Celio Larcher and Marcos Piau and Paulo Finardi and Pedro Gengo and Piero Esposito and Vinicius Caridá},
year={2023},
eprint={2308.11878},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.54 |
| AI2 Reasoning Challenge (25-Shot) | 33.79 |
| HellaSwag (10-Shot) | 55.35 |
| MMLU (5-Shot) | 25.16 |
| TruthfulQA (0-shot) | 38.50 |
| Winogrande (5-shot) | 59.43 |
| GSM8k (5-shot) | 0.99 |
- Downloads last month
- 403
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for 22h/open-cabrita3b
Spaces using 22h/open-cabrita3b 3
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard33.790
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard55.350
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard25.160
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard38.500
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard59.430
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.990