sduxz

sduxz's Stars

• lancedb/lance

  Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

  Language:Rust3.9k216

• lancedb/lancedb

  Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

  Language:Rust4.6k319

• NielsRogge/Transformers-Tutorials

  This repository contains demos I made with the Transformers library by HuggingFace.

  Language:Jupyter Notebook9.4k1.4k

• microsoft/RecAI

  Bridging LLM and Recommender System.

  Language:Jupyter Notebook57353

• webdataset/webdataset

  A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

  Language:Python2.3k187

• sz3/libcimbar

  Optimized implementation for color-icon-matrix barcodes

  Language:C++4.1k291

• NeoVertex1/SuperPrompt

  SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

  4.7k449

• OFA-Sys/Chinese-CLIP

  Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

  Language:Python4.5k462

• mlabonne/llm-datasets

  High-quality datasets, tools, and concepts for LLM fine-tuning.

  1.9k173

• eza-community/eza

  A modern alternative to ls

  Language:Rust11.9k216

• mosaicml/llm-foundry

  LLM training code for Databricks foundation models

  Language:Python4k526

• project-numina/aimo-progress-prize

  Language:Jupyter Notebook29622

• microsoft/graphrag

  A modular graph-based Retrieval-Augmented Generation (RAG) system

  Language:Python18.6k1.8k

• stopwords-iso/stopwords-en

  English stopwords collection

  152120

• goto456/stopwords

  中文常用停用词表（哈工大停用词表、百度停用词表等）

  4.7k2.2k

• baipengyan/Chinese-StopWords

  中文常用的停用词(包含百度、哈工大、四川大学等词表)

  Language:Python2525

• stopwords-iso/stopwords-zh

  Chinese stopwords collection

  13085

• cambrian-mllm/cambrian

  Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

  Language:Python1.7k113

• bilibili/Index-1.9B

  A SOTA lightweight multilingual LLM

  Language:Python89448

• zou-group/textgrad

  TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

  Language:Python1.8k150

• mira-space/Mira

  Language:Python34214

• Psycoy/MixEval

  The official evaluation suite and dynamic data release for MixEval.

  Language:Python22134

• embeddings-benchmark/mteb

  MTEB: Massive Text Embedding Benchmark

  Language:Jupyter Notebook1.9k258

• 2noise/ChatTTS

  A generative speech model for daily dialogue.

  Language:Python31.9k3.5k

• multimodal-art-projection/MAP-NEO

  Language:Python86681

• lllyasviel/IC-Light

  More relighting!

  Language:Python5.2k355

• pytorch/torchtitan

  A native PyTorch Library for large model training

  Language:Python2.5k192

• comfyanonymous/ComfyUI

  The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

  Language:Python55.2k5.8k

• huggingface/datatrove

  Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

  Language:Python2k143

• Macaronlin/LLaMA3-Quantization

  A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..

  Language:Python1647