answerdotai Goto Github PK

hqq

Official implementation of Half-Quadratic Quantization (HQQ)

imghdr2

imghdr from python stdlib

llm

Access large language models from the command-line

llm-claude-3

LLM plugin for interacting with the Claude 3 family of models

llm-ctx

Create an LLM XML context document from an llms.txt file

llm.c

LLM training in simple, raw C/CUDA

markdown_merge

Send email using markdown

meta-nbextension

Access to current notebook and cell in an nbclassic notebook

mininb

A tiny notebook experiment

mteb_arena_colbert_api

playwrightnb

Use sync mode Playwright interactively, inside a Jupyter notebook

pythonrunscript

Run python scripts, auto-installing their dependencies in cached, isolated environments

ragatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

rerankers

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

share2self

Discord user installable app to share a message by DM to self

sqlite-minutils

A fork of sqlite-utils with CLI etc removed

stitch

surreal

🗿 Mini jQuery alternative. Dependency-free animations. Locality of Behavior. Use one element or arrays transparently. Pairs with htmx. Vanilla querySelector() but better!

tinyredis

Experimental minimalist API for redis

todos-vercel

Sample FastHTML vercel app

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

tokenizers-dev

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

toolslm

Tools to make language models a bit easier to use

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vllm

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

vllm-cla

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

web2md

Convert a web page to markdown

webgpu-dawn-binaries

word2md

Paste Word, get Markdown