kongds

MoRA. MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Prompt-BERT. PromptBERT: Improving BERT Sentence Embeddings with Prompts

E5-V. E5-V: Universal Embeddings with Multimodal Large Language Models

scaling_sentemb. Scaling Sentence Embeddings with Large Language Models

LightXML. LightXML: Transformer with dynamic negative sampling for High-Performance Extreme Multi-label Text Classification

HBGL. Exploiting Global and Local Hierarchies for Hierarchical Text Classification

MIST. Improving Non-autoregressive Generation with Mixup Training

SMP. Pruning Pre-trained Language Models Without Fine-Tuning

.doom.d. Emacs Lisp