zuanki

LLM101n

LLM101n: Let's build a Storyteller

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

semantic-segmentation

SOTA Semantic Segmentation Models in PyTorch

schedule_free

Schedule-Free Optimization in PyTorch

pykan

Kolmogorov Arnold Networks

TPU-Alignment

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

CRAFT-pytorch

Official implementation of Character Region Awareness for Text Detection (CRAFT)

coding-interview-university

A complete computer science study plan to become a software engineer.

gpt-llm-trainer

dspy

DSPy: The framework for programming—not prompting—foundation models

surya

OCR, layout analysis, reading order, line detection in 90+ languages

alphageometry

milvus

A cloud-native vector database, storage for next generation AI applications

mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

optimum-nvidia

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

generative-models

Generative Models by Stability AI

Yi

A series of large language models trained from scratch by developers @01-ai

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

PhoGPT

PhoGPT: Generative Pre-training for Vietnamese (2023)

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Awesome-Deep-Graph-Clustering

Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods (papers, codes, and datasets).

clingo

🤔 A grounder and solver for logic programs.

mplcyberpunk

"Cyberpunk style" for matplotlib plots