Stars
An open protocol enabling communication and interoperability between opaque agentic applications.
An Open Source Toolkit For LLM Distillation
[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.
A package to generate summaries of long-form text and evaluate the coherence of these summaries. Official package for our ICLR 2024 paper, "BooookScore: A systematic exploration of book-length summ…
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Clothing Fashion Extraction from Music Videos or any videos of the kind.
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
OCR, layout analysis, reading order, table recognition in 90+ languages
Venice, Derived Data Platform for Planet-Scale Workloads.
Low-code framework for building custom LLMs, neural networks, and other AI models
A visual introduction to probability and statistics.
Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
Code for CVPR2021 paper: MOOD: Multi-level Out-of-distribution Detection
Implementation of Supervised Contrastive Learning with AMP, EMA, SWA, and many other tricks
Jekyll theme based on Grayscale Start Bootstrap theme
A content-first, sliding sidebar theme for Jekyll.
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
SIIM-ACR Pneumothorax Segmentation first place solution
Unsupervised text tokenizer for Neural Network-based text generation.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Local information for COVID-19 at a glance (stats, risk calculations, news, and actions)
A script for balancing predictions which helps in achieving high results on Kaggle