transformer

Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon

State-of-the-art NLP through transformer models in a modular design and consistent APIs.

TurboQuant KV cache compression plugin for vLLM — asymmetric K/V, 8 models validated, consumer GPUs

Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)

Contextualised Embeddings and Language Modelling using BERT and Friends using R

[ICCV 2023] Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment

Curated list of methods that focuses on improving the efficiency of diffusion models

Transformer Networks for Pedestrian Detection

RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!

Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.

A Step-by-Step Implementation of RAPTOR based RAG implementation

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

AthenaOS is a next generation AI-native operating system managed by Swarms of AI Agents

A tiny language model that talks like a house cat named Miso.

TMLR | This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms.

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

A Multimodal Transformer: Fusing Clinical Notes With Structured EHR Data for Interpretable In-Hospital Mortality Prediction

Predict the Body Mass Index with one image of a human face, with state-of-the-art results.

Simple and lightweight tool to fine-tune GPT models (like GPT-2 and GPT-Neo) using your own data — built with Python and Transformers. Adapt powerful language models to your domain with ease.