kaisugi

kaisugi's Stars

• rasbt/LLMs-from-scratch

  Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

  Language:Jupyter Notebook33.3k3601064k

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python30.6k2495.3k4.6k

• unslothai/unsloth

  Finetune Llama 3.2, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

  Language:Python18.4k1291k1.3k

• joelparkerhenderson/architecture-decision-record

  Architecture decision record (ADR) examples for software planning, IT leadership, and template documentation

  12.3k234162.5k

• huggingface/chat-ui

  Open source codebase powering the HuggingChat app

  Language:TypeScript7.6k845891.1k

• ragapp/ragapp

  The easiest way to use Agentic RAG in any enterprise

  Language:TypeScript3.9k28102414

• rom1504/img2dataset

  Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

  Language:Python3.7k31261339

• pytorch/torchtitan

  A native PyTorch Library for large model training

  Language:Python2.6k42178205

• mlfoundations/dclm

  DataComp for Language Models

  Language:HTML1.2k3863107

• illuin-tech/colpali

  The code used to train and run inference with the ColPali architecture.

  Language:Python1.1k1472103

• huggingface/evaluation-guidebook

  Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

  8167350

• wasiahmad/Awesome-LLM-Synthetic-Data

  A reading list on LLM based Synthetic Data Generation 🔥

  79613049

• fmaclen/hollama

  A minimal web-UI for talking to Ollama servers

  Language:TypeScript481613040

• ibm-aur-nlp/PubTabNet

  Language:Jupyter Notebook413282379

• joeraut/latex2image-web

  LaTeX to image converter with web UI using Node.js / Docker

  Language:JavaScript2334638

• py-pdf/benchmarks

  Benchmarking PDF libraries

  Language:Python2265911

• minsing-jin/Korean-SAT-LLM-Leaderboard

  Korean SAT leader board

  Language:Jupyter Notebook962104

• takahashim/md2review

  a converter from Markdown into Re:VIEW, using redcarpet

  Language:Ruby829411

• esrille/ibus-hiragana

  ひらがなIME for IBus

  Language:Python7051884

• 34j/best-of-lean4

  A list of awesome lean4 projects. Feel free to add your project.

  62534

• DeNA/dify-google-cloud-terraform

  Terraform configuration for deploying Dify on Google Cloud with scalability, high availability, and production-level readiness.

  Language:HCL29316

• llm-jp/text2dataset

  Easily turn large English text datasets into Japanese text datasets using open LLMs.

  Language:Python140

• embeddings-benchmark/leaderboard

  Code for the MTEB leaderboard

  Language:Python1321710

• Aratako/Japanese-RP-Bench

  Language:Jupyter Notebook70

• dahlia/fedify-microblog-tutorial-ja

  『自分だけのフェディバースのマイクロブログを作ろう！』のAsciiDocのソースコード

  Language:Shell7

• hodanov/stable-diffusion-cli-on-modal

  This is a script for running Stable Diffusion on Modal.

  Language:Python70

• MMMU-Japanese-Benchmark/JMMMU

  The official repository for the website scripts of "JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark"

  Language:TypeScript2

• nii-nlp/med-eval

  Evaluation Pipeline for medical tasks.

  Language:Python20

• fjm2u/assetGenie

  Language:TypeScript1

• sociocom/TNM-Classifier-Tester

  Language:Python1