Roland Tannous

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Unsloth Fine-tuning Notebooks for Google Colab, Kaggle, Hugging Face and more.

test colab for ui

Utils for Unsloth

test studio structure

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

test repo for docker packages

:mag: Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT and alike). Haystack offers production-ready tools to quickly build complex decision making, question answering, semantic search, text generation applications, and more.

No description provided.

OCR, layout analysis, reading order, table recognition in 90+ languages

Convert PDF to markdown + JSON quickly with high accuracy

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Introduction to ML packages for the 6.86x course

Python Debugging with pdb

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

Chat Templates for 🤗 HuggingFace Large Language Models

nvim configuration directory

Practice notebooks for torch/pytorch

GoTorchX is a comprehensive Go binding for PyTorch that provides high-performance deep learning capabilities in idiomatic Go.

Exploring explainable machine learning with a focus on Shapley additive explanations

gradio slideshow generator demo

Comparing performance of rapids cudf with pandas and polars

Experiments exploring neurosymbolic programming approaches

mit introduction to deeplearning 2025 course edition code experiments

FlashInfer minp-sampling tests

Neuro-Symbolic AI with Knowledge Graph | "True Reasoning" through data and logic 🌿🌱🐋🌍

Nuxt, nuxt-content

Nuxt3 base configuration template. Includes pinia, tailwindcss, vitest, typescript, nuxt-ui and more

what type of inference is planning paper

A nearly-live implementation of OpenAI's Whisper.