bala-git9
Follow
Stars
All Algorithms implemented in Python
Fine-tuning & Reinforcement Learning for LLMs. ๐ฆฅ Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
A community-maintained Python framework for creating mathematical animations.
An autonomous agent that conducts deep research on any data using any LLM providers.
Fast and memory-efficient exact attention
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Minimal and clean examples of machine learning algorithms implementations
A library to generate LaTeX expression from Python code.
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
Count the MACs / FLOPs of your PyTorch model.
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
๐ค ๐๐ฒ๐ฎ๐ฟ๐ป for ๐ณ๐ฟ๐ฒ๐ฒ how to ๐ฏ๐๐ถ๐น๐ฑ an end-to-end ๐ฝ๐ฟ๐ผ๐ฑ๐๐ฐ๐๐ถ๐ผ๐ป-๐ฟ๐ฒ๐ฎ๐ฑ๐ ๐๐๐ & ๐ฅ๐๐ ๐๐๐๐๐ฒ๐บ using ๐๐๐ ๐ข๐ฝ๐ best practices: ~ ๐ด๐ฐ๐ถ๐ณ๐ค๐ฆ ๐ค๐ฐ๐ฅ๐ฆ + 12 ๐ฉ๐ข๐ฏ๐ฅ๐ด-๐ฐ๐ฏ ๐ญ๐ฆ๐ด๐ด๐ฐ๐ฏ๐ด
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
Avalanche: an End-to-End Library for Continual Learning based on PyTorch.
PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.
The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".
PyCIL: A Python Toolbox for Class-Incremental Learning
Implementation of "SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks"
Update arXiv papers about Spiking Neural Networks daily.
Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory
Tenstorrent's MLIR Based Compiler. We aim to enable developers to run AI on all configurations of Tenstorrent hardware, through an open-source, general, and performant compiler.
An event-driven learning algorithm for spiking neural networks