rawsh-rubrik's Stars
PRIME-RL/PRIME
merveenoyan/smol-vision
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
tursodatabase/limbo
Limbo is a work-in-progress, in-process OLTP database management system, compatible with SQLite.
codestoryai/sidecar
Sidecar is the AI brains for the Aide editor and works alongside it, locally on your machine
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training
All-Hands-AI/OpenHands
🙌 OpenHands: Code Less, Make More
allenai/open-instruct
moshe/asonic
async python client for the sonic search backend
valeriansaliou/sonic
🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.
microsoft/aici
AICI: Prompts as (Wasm) Programs
allenai/reward-bench
RewardBench: the first evaluation tool for reward models.
mixedbread-ai/batched
kuleshov/cornell-cs5785-2020-applied-ml
Teaching materials for the applied machine learning course at Cornell Tech (online edition)
srush/awesome-o1
A bibliography and survey of the papers surrounding o1
erikbern/ann-benchmarks
Benchmarks of approximate nearest neighbor libraries in Python
mk-fg/systemd-cgroup-nftables-policy-manager
Tool to add/update nftables cgroupv2 rules for systemd-managed unit cgroups (slices, services, scopes)
vscode-neovim/vscode-neovim
Vim mode for VSCode, powered by Neovim
Inspirateur/Fast-BM25
a fast implementation of BM25
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation
kyutai-labs/moshi
ictnlp/LLaMA-Omni
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
Anush008/fastembed-rs
Rust library for generating vector embeddings, reranking locally
xorbitsai/inference
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
michaelfeil/infinity
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
OpenBMB/MiniCPM-V
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Cinnamon/kotaemon
An open-source RAG-based tool for chatting with your documents.
RLHFlow/RLHF-Reward-Modeling
Recipes to train reward model for RLHF.
jehna/humanify
Deobfuscate Javascript code using ChatGPT
knowitall/reverb
Web-Scale Open Information Extraction