transformers

◉ Universal Intelligence: AI made simple.

[TCAD'23] AccelTran: A Sparsity-Aware Accelerator for Transformers

music genre classification : LSTM vs Transformer

Our open source implementation of MiniLMv2 (https://aclanthology.org/2021.findings-acl.188)

[ICCV'23 Oral] Unmasking Anomalies in Road-Scene Segmentation

Add CRF or LSTM+CRF for huggingface transformers bert to perform better on NER task. It is very simple to use and very convenient to customize

Build foundation model for RNA or DNA data

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.

Topic Inference with Zeroshot models

Persian Bert For Long-Range Sequences

An interpretable foundation model of the patient clinical timeline: event forecasting, calibrated time-to-event alerts, and concept-level interpretability, benchmarked head-to-head against tuned GBMs, tabular foundation models, and survival baselines on MIMIC-IV, eICU, and GEMINI via the MEDS standard.

CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations, ICCV 2021

Error Correction Code Transformer

Speakerbox: Fine-tune Audio Transformers for speaker identification.

[ICLR 2024 Spotlight] This is the official code for the paper "SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training"

Bilingual term extractor

使用LLaMA-Factory微调多模态大语言模型的示例代码 Demo of Finetuning Multimodal LLM with LLaMA-Factory

Code for the paper "On the Expressivity Role of LayerNorm in Transformers' Attention" (Findings of ACL'2023)

A numpy implementation of the Transformer model in "Attention is All You Need"

Tune efficiently any LLM model from HuggingFace using distributed training (multiple GPU) and DeepSpeed. Uses Ray AIR to orchestrate the training on multiple AWS GPU instances