Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Optimizing inference proxy for LLMs
🚀 The fast, Pythonic way to build MCP servers and clients
Environments for LLM Reinforcement Learning
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Official Implementation of "KBLaM: Knowledge Base augmented Language Model"
A python package made to generate sequences (greedy and beam-search) from Pytorch (not necessarily HF transformers) models.
Excalidraw app for mac. Powered by pure SwiftUI.
Building LLMs from scratch following the book from S. Raschka
Named Entity Recognition with an decoder-only (autoregressive) LLM using HuggingFace
Command line program to validate and convert CITATION.cff files.
A general fine-tuning kit geared toward image/video/audio diffusion models.
CLI/GUI for managing the battery charging status for Apple silicon (M1, M2, M3) Macs
Machine Learning Journal for Intermediate to Advanced Topics.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Finetune a pre-trained GPT-2 model to generate personalized product recommendations for users, based on product reviews and metadata
The simplest, most straightforward way to learn ML for free.
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.
Reference implementation for DPO (Direct Preference Optimization)
Machine Learning Engineering Open Book
Full Stack Graph Machine Learning: Theory, Practice, Tools and Techniques
Distributed Reinforcement Learning accelerated by Lightning Fabric
NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day
Scientific Python Library Development Guide and Cookiecutter
Large Language Models for All, 🦙 Cult and More, Stay in touch !
Fast & Simple repository for pre-training and fine-tuning T5-style models








