Skip to content
View mmarius's full-sized avatar
👨‍💻
👨‍💻

Highlights

  • Pro

Block or report mmarius

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

The best ChatGPT that $100 can buy.

Python 36,207 4,247 Updated Nov 5, 2025

Fully open data curation for reasoning models

Python 2,136 177 Updated Sep 3, 2025
Python 7 Updated Oct 3, 2025

Code to reproduce the experiments in the paper Training on the Test Task Confounds Evaluation and Emergence.

Jupyter Notebook 11 1 Updated Dec 3, 2024

Reproducible, flexible LLM evaluations

Python 264 51 Updated Oct 27, 2025

Modeling, training, eval, and inference code for OLMo

Python 6,098 669 Updated Oct 24, 2025

PyTorch building blocks for the OLMo ecosystem

Python 316 58 Updated Nov 9, 2025

AllenAI's post-training codebase

Python 3,286 454 Updated Nov 9, 2025

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Python 4,732 273 Updated Jul 18, 2025
Python 37 8 Updated Dec 19, 2024

Improving Alignment and Robustness with Circuit Breakers

Jupyter Notebook 240 38 Updated Sep 24, 2024

PyTorch native post-training library

Python 5,581 679 Updated Nov 9, 2025

Machine Learning Engineering Open Book

Python 15,663 957 Updated Oct 27, 2025

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Python 10,120 975 Updated Jul 1, 2024

Minimalistic large language model 3D-parallelism training

Python 2,303 254 Updated Sep 3, 2025

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

R 6,908 281 Updated Sep 3, 2025

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Python 5,673 486 Updated Nov 7, 2025

The hub for EleutherAI's work on interpretability and learning dynamics

Jupyter Notebook 2,664 195 Updated Jun 9, 2025

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Python 20,004 2,086 Updated Nov 5, 2025

Cramming the training of a (BERT-type) language model into limited compute.

Python 1,351 102 Updated Jun 13, 2024

Algorithmically create or extend categorical colour palettes

Python 226 8 Updated Oct 11, 2025

An autoregressive character-level language model for making more things

Python 3,394 863 Updated Jun 4, 2024

Figure sizes, font sizes, fonts, and more configurations at minimal overhead. Fix your journal papers, conference proceedings, and other scientific publications.

Python 713 30 Updated Jul 14, 2025

Code to run the TILT transfer learning experiments

Python 32 10 Updated Feb 13, 2021

NAACL 2022: MCSE: Multimodal Contrastive Learning of Sentence Embeddings

Python 57 8 Updated Jun 10, 2024

A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.

Python 75 11 Updated Aug 9, 2024

An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"

Python 131 18 Updated Apr 23, 2022

This code accompanies the paper "Bayesian Framework for Information-Theoretic Probing" published in EMNLP 2021.

Python 10 Updated Aug 23, 2021

Train Dense Passage Retriever (DPR) with a single GPU

Python 133 21 Updated Jun 16, 2021

Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

Python 415 26 Updated Mar 26, 2024
Next