downstream-tasks 开源项目推荐（21 个）

hooshvare /parsbert

🤗 ParsBERT: Transformer-based Model for Persian Language Understanding

SaeedShurrab /awesome-self-supervised-learning-in-medical-imaging

本库主要用于列出医学图像计算领域自我监督学习应用的最新研究进展

ychuest /Awesome-LLMs-meet-genomes

Explore a comprehensive collection of basic theories, applications, papers, and best practices about Large Language Models (LLMs) in genomes.

yan-hao-tian /ConTNet

该仓库包含代码“ConTNet：为什么不同时使用卷积和变换器？”

LucaOne /LucaOneTasks

The project of the downstream tasks based on LucaOne's Embedding.

amazon-science /probconserv

Datasets and code for results presented in the ProbConserv paper

Audio-WestlakeU /SAR-SSL

A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer” [TASLP 2024]

soda-inria /sepal

Repository for SEPAL: Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning

IBM /AutoVP

[ICLR24] "AutoVP: An Automated Visual Prompting Framework and Benchmark" by Hsi-Ai Tsao*, Lei Hsiung*, Pin-Yu Chen, Sijia Liu, and Tsung-Yi Ho.

LSSI-ETH /plmfit

PLMFit platform for TL on PLMs

2U1 /DINOv2-Finetune

An open-source implementaion for fine-tuning DINOv2 by Meta.

cleanzr /representr

Create representative records post-record linkage

conditionWang /Split_Adaptation

This is the code implementation of CVPR-2025 paper: Split Adaptation for Pre-trained Vision Transformers.

firojalam /LlamaLens

This repository contains the resources, code, and documentation for LlamaLens, a specialized multilingual large language model (LLM) designed to analyze news and social media content effectively. LlamaLens supports multiple languages, including Arabic, English, and Hindi, and is tailored for diverse tasks such as sentiment analysis, misinformation.

U4RASD /NeoAraBERT

NeoAraBERT is a state-of-the-art open-source Arabic text-embedding model built on the NeoBERT architecture.

Udrasht /ELMO-Embeddings-from-Language-Models

This repository contains implementations of ELMo (Embeddings from Language Models) models trained on a news dataset. Additionally, it includes a classification task using ELMo embeddings.

michaelo /prosit

A simple project setup tool.

shiva-s936 /ELMo-Deep-Contextualized-Word-Representations

An implementation of ELMo embeddings using PyTorch, featuring stacked Bi-LSTMs for contextualized word representations. Pretrained on bidirectional language modeling and evaluated on the AG News dataset for text classification, achieving metrics like accuracy, F1, and precision.

roissyahf /elt-yelp-business-gcp

End-to-end Data Analytics Yelp Business Review Project

JackTheProgrammer /Minds14-based-Wav2Vec2-Fine-Tuned

Fine tuned facebook/Wav2Vec2-960h-base for the purpose of speech based task detection relevant to banking and finances, of an individual.