paper-with-me

홈 › Papers

TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese

2024-01-30 · Nicholas Kluge Corrêa, Sophia Falk, Shiza Fatimah, Aniket Sen, Nythamar de Oliveira

Large language models (LLMs) have significantly advanced natural language processing, but their progress has yet to be equal across languages. While most LLMs are trained in high-resource languages like English, multilingual models generally underperform monolingual ones. Additionally, aspects of their multilingual foundation sometimes restrict the byproducts they produce, like computational demands and licensing regimes. In this study, we document the development of open-foundation models tailored for use in low-resource settings, their limitations, and their benefits. This is the TeenyTinyLlama pair: two compact models for Brazilian Portuguese text generation. We release them under the permissive Apache 2.0 license on GitHub and Hugging Face for community use and further development. See https://github.com/Nkluge-correa/TeenyTinyLlama

📄 PDF Abstract BibTeX arXiv:2401.16640

Code (2)

nkluge-correa/teenytinyllama 공식 구현 pytorch
ruanchaves/eplm

Tasks

Text Generation

Similar Papers 제목 키워드 기반

TinyLlama: An Open-Source Small Language Model

2024-01-04 · Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, Wei Lu

We present TinyLlama, a compact 1.1B language model pretrained on around 1 trillion tokens for approximately 3 epochs. Building on the architecture and tokenizer of Llama 2, TinyLlama leverages various advances contribut…

Computational EfficiencyLanguage ModelingLanguage Modellingmodel+1

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

2023-12-28 · Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye 외

In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks. Despite their prowess, the closed-source nature and com…

Computational EfficiencyImage CaptioningLanguage ModelingLanguage Modelling+6

TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance

2023-09-21 · ICCV 2023 1 · Kan Wu, Houwen Peng, Zhenghong Zhou, Bin Xiao 외

In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models. The method introduces two core techniques: affinity mimicking and weight inheritance.…

A Study on Tiny YOLO for Resource Constrained Xray Threat Detection

2023-09-27 · Raghav Ambati, Ayon Borthakur

This paper implements and analyzes multiple networks with the goal of understanding their suitability for edge device applications such as X-ray threat detection. In this study, we use the state-of-the-art YOLO object de…

object-detectionObject Detection

Tiny language models

2025-07-20 · Ronit D. Gross, Yarden Tzach, Tal Halevi, Ella Koresh 외 arxiv

A prominent achievement of natural language processing (NLP) is its ability to understand and generate meaningful human language. This capability relies on complex feedforward transformer block architectures pre-trained …