Viktor Ferenczi (viktor-ferenczi)

viktor-ferenczi

Geek Repo

Company:AI-42 Sweden AB

Location:Sweden

Home Page:http://www.linkedin.com/in/viktorferenczi

Github PK Tool:Github PK Tool

Viktor Ferenczi's starred repositories

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Language:SvelteLicense:MITStargazers:30690Issues:169Issues:1474

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonLicense:MITStargazers:19133Issues:297Issues:1332

fabric

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Language:PythonLicense:MITStargazers:18958Issues:271Issues:310

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Language:PythonLicense:MITStargazers:17070Issues:204Issues:612

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:14571Issues:127Issues:3343

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Language:PythonLicense:MITStargazers:8719Issues:81Issues:35

CopilotKit

A framework for building custom AI Copilots 🤖 in-app AI chatbots, in-app AI Agents, & AI-powered Textareas.

Language:TypeScriptLicense:MITStargazers:7718Issues:61Issues:93

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Language:C++License:Apache-2.0Stargazers:7422Issues:85Issues:1562

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Language:PythonLicense:MITStargazers:5970Issues:37Issues:849

lark

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

Language:PythonLicense:MITStargazers:4618Issues:59Issues:881

moondream

tiny vision language model

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:4504Issues:50Issues:93

promptfoo

Test your prompts, agents, and RAGs. Use LLM evals to improve your app's quality and catch problems. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

Language:TypeScriptLicense:MITStargazers:3564Issues:18Issues:483

gprof2dot

Converts profiling output to a dot graph.

Language:PythonLicense:LGPL-3.0Stargazers:3145Issues:79Issues:57

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Language:PythonLicense:Apache-2.0Stargazers:2806Issues:30Issues:286

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Language:PythonLicense:Apache-2.0Stargazers:2067Issues:22Issues:169

parsimonious

The fastest pure-Python PEG parser I can muster

Language:PythonLicense:MITStargazers:1788Issues:42Issues:162

Awesome-GPT-Store

Custom GPT Store - A collection of major GPTS available in public

ATLAS

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

Language:PythonLicense:Apache-2.0Stargazers:866Issues:21Issues:7
Language:PythonLicense:Apache-2.0Stargazers:834Issues:39Issues:62

flashinfer

FlashInfer: Kernel Library for LLM Serving

Language:CudaLicense:Apache-2.0Stargazers:772Issues:13Issues:70

super-json-mode

Low latency JSON generation using LLMs ⚡️

Language:Jupyter NotebookStargazers:363Issues:2Issues:5

quiet-star

Code for Quiet-STaR

Language:PythonLicense:Apache-2.0Stargazers:321Issues:12Issues:7

indydevtools

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

lark-grammars

Grammars suitable for lark parser and Hypothesis

Language:PythonLicense:ISCStargazers:41Issues:4Issues:2

tabbyAPI-gradio-loader

A simple Gradio WebUI for loading/unloading models and loras in tabbyAPI.

Language:PythonLicense:MITStargazers:11Issues:1Issues:1

ST-tabbyAPI-loader

Loader extension for tabbyAPI in SillyTavern

Language:JavaScriptStargazers:6Issues:1Issues:4

ReeditShipManagement

Broad ship management solution tailor made for Draconis Expanse.

Language:C#Stargazers:3Issues:1Issues:0

SE-ModDebugger

Modifies the Space Engineers IL Checker to aid in the debugging of mods

Language:C#License:CC0-1.0Stargazers:2Issues:0Issues:0
Language:C#Stargazers:2Issues:0Issues:0

wolfram-model-variety

Codes to investigate Leibnizian ideas in Wolfram Model.

Language:C++License:GPL-3.0Stargazers:1Issues:0Issues:0