PhoGPT: Generative Pre-training for Vietnamese

TL;DR

PhoGPT is a new Vietnamese language model series with a 4B-parameter base and chat variant, trained on extensive Vietnamese data, demonstrating superior performance over previous models.

Contribution

Introduction of PhoGPT, a state-of-the-art 4B-parameter Vietnamese language model and its chat variant, trained from scratch and fine-tuned on instructional data.

Findings

PhoGPT outperforms previous open-source Vietnamese models.

The base model is trained on 102B tokens with an 8192 context window.

The chat variant is fine-tuned on 70K prompts and 290K conversations.

Abstract

We open-source a state-of-the-art 4B-parameter generative model series for Vietnamese, which includes the base pre-trained monolingual model PhoGPT-4B and its chat variant, PhoGPT-4B-Chat. The base model, PhoGPT-4B, with exactly 3.7B parameters, is pre-trained from scratch on a Vietnamese corpus of 102B tokens, with an 8192 context length, employing a vocabulary of 20480 token types. The chat variant, PhoGPT-4B-Chat, is the modeling output obtained by fine-tuning PhoGPT-4B on a dataset of 70K instructional prompts and their responses, along with an additional 290K conversations. In addition, we also demonstrate its superior performance compared to previous open-source models. Our PhoGPT models are available at: https://github.com/VinAIResearch/PhoGPT