Stars
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
An animated number component for React, Vue, and Svelte.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Aidan Bench attempts to measure <big_model_smell> in LLMs.
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
OCR, layout analysis, reading order, table recognition in 90+ languages
an implementation of Self-Extend, to expand the context window via grouped attention
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
Draws simple SVG flow chart diagrams from textual representation of the diagram
A Dataset of Python Challenges for AI Research
Mamba-Chat: A chat LLM based on the state-space model architecture 🐍
Reference implementation for DPO (Direct Preference Optimization)
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
DeepSeek Coder: Let the Code Write Itself
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
LostRuins / koboldcpp
Forked from ggerganov/llama.cppRun GGUF models easily with a KoboldAI UI. One File. Zero Install.
Universal LLM Deployment Engine with ML Compilation
Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
jondurbin / qlora
Forked from artidoro/qloraQLoRA: Efficient Finetuning of Quantized LLMs