Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

使用预训练语言模型BERT做中文NER

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

Scale LLM Engine public repository

使用预训练语言模型ALBERT做中文NER

ImageNet pre-trained models with batch normalization for the Caffe framework

Fine-tuning code for CLIP models

[SOTA] [92% acc] 786M-8k-44L-32H multi-instrumental music transformer with true full MIDI instruments range, efficient encoding, octo-velocity and outro tokens

Use FastSpeech2 and HiFi-GAN to easily perform end-to-end Korean speech synthesis.

TensorFlow Implementation of Manifold Regularized Convolutional Neural Networks.

🚂 Fine-tune OpenAI models for text classification, question answering, and more

Training and fine-tuning flan-t5-small model based on provided text

Mistral model inference and fine-tune

Fine tuning LLaMA-2 model on provided text data

Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.

Flan-t5 model fine tune LoRA and Langchain

[Bachelor Graduation Project] Use Xception model for face anti-spoofing

This repository contains the source code for the first and the second task of DeftEval 2020 competition, used by the University Politehnica of Bucharest (UPB) team to train and evaluate the models.

🌹[ICML 2024] Selecting Large Language Model to Fine-tune via Rectified Scaling Law

Geometric Parametrization GmP-Inf-CLIP modification of: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training scheme.