Daniel Tiarks (dtiarks)

dtiarks

Geek Repo

Company:Cambrion

Location:Munich

Home Page:https://docs.cambrion.io

Github PK Tool:Github PK Tool

Daniel Tiarks's starred repositories

LLM_convert_receipt_image-to-json_or_xml

Finetune LLM to convert an invoice or receipt image to receipt XML or JSON object.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:18Issues:0Issues:0

gritql

GritQL is a query language for searching, linting, and modifying code.

Language:RustLicense:MITStargazers:1835Issues:0Issues:0

Brazilian-Identity-Document-Dataset

Brazilian Identity Document Dataset (BID Dataset): The first public dataset of Brazilian identification documents.

Stargazers:50Issues:0Issues:0

bruno

Opensource IDE For Exploring and Testing Api's (lightweight alternative to postman/insomnia)

Language:JavaScriptLicense:MITStargazers:17446Issues:0Issues:0

fsdp_qlora

Training LLMs with QLoRA + FSDP

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1031Issues:0Issues:0

streamlit-drawable-canvas

Do you like Quick, Draw? Well what if you could train/predict doodles drawn inside Streamlit? Also draws lines, circles and boxes over background images for annotation.

Language:TypeScriptLicense:MITStargazers:513Issues:0Issues:0

streamlit-cropper

A simple image cropper for Streamlit

Language:TypeScriptLicense:MITStargazers:167Issues:0Issues:0

s3proxy

Access other storage backends via the S3 API

Language:JavaLicense:Apache-2.0Stargazers:1573Issues:0Issues:0

kernel_tuner

Kernel Tuner

Language:PythonLicense:Apache-2.0Stargazers:234Issues:0Issues:0

based

Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"

Language:PythonLicense:Apache-2.0Stargazers:148Issues:0Issues:0

lancedb

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

Language:PythonLicense:Apache-2.0Stargazers:2575Issues:0Issues:0

polars-fuzzy-match

Polars extension for fzf-style fuzzy matching

Language:PythonLicense:MITStargazers:11Issues:0Issues:0

cookiecutter-hypermodern-python

Hypermodern Python Cookiecutter

Language:PythonLicense:MITStargazers:1704Issues:0Issues:0

R2R

An open-source framework for building, deploying and optimizing (Retrieval-Augmented Generation) RAG systems.

Language:PythonLicense:MITStargazers:970Issues:0Issues:0

verneuil

Verneuil is a VFS extension for SQLite that asynchronously replicates databases to S3-compatible blob stores.

Language:CLicense:MITStargazers:388Issues:0Issues:0

sslcontext-kickstart

🔐 A lightweight high level library for configuring a http client or server based on SSLContext or other properties such as TrustManager, KeyManager or Trusted Certificates to communicate over SSL TLS for one way authentication or two way authentication provided by the SSLFactory. Support for Java, Scala and Kotlin based clients with examples. Available client examples are: Apache HttpClient, OkHttp, Spring RestTemplate, Spring WebFlux WebClient Jetty and Netty, the old and the new JDK HttpClient, the old and the new Jersey Client, Google HttpClient, Unirest, Retrofit, Feign, Methanol, Vertx, Scala client Finagle, Featherbed, Dispatch Reboot, AsyncHttpClient, Sttp, Akka, Requests Scala, Http4s Blaze, Kotlin client Fuel, http4k Kohttp and Ktor. Also gRPC, WebSocket and ElasticSearch examples are included

Language:JavaLicense:Apache-2.0Stargazers:462Issues:0Issues:0

regex-constrained-decoding

Fast, High-Fidelity LLM Decoding with Regex Constraints

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:6Issues:0Issues:0

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Language:PythonLicense:Apache-2.0Stargazers:13286Issues:0Issues:0

ReAlign

Reformatted Alignment

Language:JavaScriptStargazers:67Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:6593Issues:0Issues:0

json_repair

A python module to repair broken JSON, very useful with LLMs

Language:PythonLicense:MITStargazers:184Issues:0Issues:0

libnpy

C++ library for reading and writing of numpy's .npy files

Language:C++License:MITStargazers:329Issues:0Issues:0
Language:Jupyter NotebookStargazers:117Issues:0Issues:0

btop

A monitor of resources

Language:C++License:Apache-2.0Stargazers:15880Issues:0Issues:0

llmware

Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.

Language:PythonLicense:Apache-2.0Stargazers:2947Issues:0Issues:0

tantivy-py

Python bindings for Tantivy

Language:RustLicense:MITStargazers:194Issues:0Issues:0

seaweedfs

SeaweedFS is a fast distributed storage system for blobs, objects, files, and data lake, for billions of files! Blob store has O(1) disk seek, cloud tiering. Filer supports Cloud Drive, cross-DC active-active replication, Kubernetes, POSIX FUSE mount, S3 API, S3 Gateway, Hadoop, WebDAV, encryption, Erasure Coding.

Language:GoLicense:Apache-2.0Stargazers:20843Issues:0Issues:0

ezlocalai

ezlocalai is an easy to set up local artificial intelligence server with OpenAI Style Endpoints.

Language:Jupyter NotebookLicense:MITStargazers:52Issues:0Issues:0

Vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Language:PythonStargazers:1672Issues:0Issues:0

proton

A streaming SQL engine, a fast and lightweight alternative to Apache Flink, 🚀 powered by ClickHouse.

Language:C++License:Apache-2.0Stargazers:1241Issues:0Issues:0