Patrick Haller

A curated list of resources related to linear attention mechanisms.

New and clean Neovim config

No description provided.

No description provided.

Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible experimentation and exploration.

🐸 Debug faster than a frog catches a fly

No description provided.

A framework for few-shot evaluation of language models.

A solarized color theme for VS Code

Lsp Plugin for working with Python virtual environments

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Minimalistic large language model 3D-parallelism training

Just another minimalist Jekyll theme which designed for technical writing blog.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Pretraining code for a large-scale depth-recurrent language model

🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

[LREC-Coling 2024] PECC: Problem Extraction and Coding Challenges

No description provided.

Debugging made easy again with this delicious tool!

A HuggingFace compatible xLSTM trainer.

A character tokenizer for Hugging Face Transformers

Official repository of the xLSTM.

Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.

No description provided.

phgrad - Cause there are not enough unusable autograd libraries in python

No description provided.

Inference code for LLaMA models

More powerful and customizable tables in Typst

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

Own shell implementation in Rust