🤗 Benchmark Large Language Models Reliably On Your Data

An open source implementation of CLIP (With TULIP Support)

Convert any PDF into a podcast episode!

A self-paced course to learn Rust, one exercise at a time.

NVIDIA Linux open GPU with P2P support

A PDF to Markdown converter

Stable Diffusion web UI

vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs

Best practice for training LLaMA models in Megatron-LM

QLoRA with Enhanced Multi GPU Support

Finetune a LLM to speak like you based on your WhatsApp Conversations

Llama 2 Everywhere (L2E)

A platform that uses the OpenAI API to quickly build an AI knowledge base, supporting many-to-many relationships.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Inference TinyLlama models on ncnn

Inference Llama 2 in one file of pure Python

QLoRA: Efficient Finetuning of Quantized LLMs

Ongoing research training transformer language models at scale, including: BERT & GPT-2

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

Quick Start LLaMA models with multiple methods, and fine-tune 7B/65B with One-Click.

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Code for I3D Feature Extraction

This repository is intended to host tools and demos for ActivityNet

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

YOLOv5, CrowdHuman, Trained model

This repository contains the source code of TeamUW in Track 1 and Track 3 at the NVIDIA AI City Challenge Workshop at CVPR 2018.

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

traffic light recognition system for ADAS

Classify Traffic Signs.