singhranjodh

Prompt-Engineering-Guide

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

minbpe

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

magika

Detect file content types with deep learning

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

axolotl

Go ahead and axolotl questions

gpt-fast

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

cutlass

CUDA Templates for Linear Algebra Subroutines

torchtune

A Native-PyTorch Library for LLM Fine-tuning

leafmap

A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment

deepsparse

Sparsity-aware deep learning inference runtime for CPUs

jepa

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

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

localllm

SoM

Set-of-Mark Prompting for LMMs

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

adapter-bert

long-form-factuality

Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

EfficientLoFTR

LLM-Workshop

LLM Workshop by Sourab Mangrulkar

ao

Native PyTorch library for quantization and sparsity

gaussian-head

Official repository for 'GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation'

indicnlp_corpus

Description Describes the IndicNLP corpus and associated datasets

fast-llm.rs

RAGTruth

Github repository for "RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models"

languagecodec_tmp

Temporary anonymous version

hyllama

llama.cpp gguf file parser for javascript

torch-bnb-fp4

Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops