Making large AI models cheaper, faster and more accessible
- deep-learning
- hpc
- large-scale
- data-parallelism
111,821 visible repositories in the index
1–24 of 50 · Most stars
Making large AI models cheaper, faster and more accessible
An open source implementation of CLIP.
File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
Self hosted FLOSS fitness/workout, nutrition and weight tracker
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
A scriptable music downloader for Qobuz, Tidal, SoundCloud, and Deezer
:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
LPIPS metric. pip install lpips
FLARE Obfuscated String Solver - Automatically extract obfuscated strings from malware.
A collection of loss functions for medical image segmentation
Insane(ly slow but wicked good) PNG image optimization
Machine Learning meets ketosis: how to effectively lose weight
Code for visualizing the loss landscape of neural nets
Siamese and triplet networks with online pair/triplet mining in PyTorch
Machine learning glossary
🔥🔥🔥 专注于YOLO11,YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型,Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀
A tool for converting dictionary files aka glossaries. Mainly to help use our offline glossaries in any Open Source dictionary we like on any operating system / device.
A desktop music library builder that turns Spotify, Youtube Music Apple Music, Amazon Music, Tidal, Qobuz, and Deezer links into fully tagged local library in FLAC, ALAC, Dolby Atmos, AAC, or MP3.
A complete Lossless and Hi-Res music downloader for Qobuz
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Decky plugin to streamline installation and usage of lsfg-vk; the Lossless Scaling compatibility layer for linux
A PyTorch Toolbox for Face Recognition