kristiankielhofner Goto Github PK

air-appsmith-test

alpaca-lora

Instruct-tune LLaMA on consumer hardware

bitbeast

Experiments with Model Training, Deployment & Monitoring

bowser

A WebRTC browser for iOS developed in the open

contrastors

Train Models Contrastively in Pytorch

deepspeech

A TensorFlow implementation of Baidu's DeepSpeech architecture

dejavu

Audio fingerprinting and recognition in Python

docker-rtlsdrairband

Docker container to run rtlsdir-airband + ice cast to stream ATC audio locally or to a remote server

docker-webone

WebOne HTTP1.X Proxy

doctr

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

esp-adf

Espressif Audio Development Framework

esp-box

The ESP-BOX is a new generation AIoT development platform released by Espressif Systems.

ethminer

Ethereum miner with OpenCL, CUDA and stratum support

ffmpeg.wasm

FFmpeg for browser and node, powered by WebAssembly

ffmpeg.wasm-core

Mirror of git://source.ffmpeg.org/ffmpeg.git

freeswitch

The World's First Cross-Platform Scalable FREE Multi-Protocol Soft Switch

gptq-for-llama

4 bits quantization of LLaMa using GPTQ

h2ogpt

Private Q&A and summarization of documents+images or chat with local GPT, 100% private, Apache 2.0. Supports LLaMa2, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/

itu-t_pesq

kaldi

This is the official location of the Kaldi project.

kaldiio

A pure python module for reading and writing kaldi ark files

libsrtp

Library for SRTP (Secure Realtime Transport Protocol)

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

model_analyzer

Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.

model_navigator

The Triton Model Navigator is a tool that provides the ability to automate the process of model deployment on the Triton Inference Server.

nemo

NeMo: a toolkit for conversational AI

openai_trtllm

OpenAI compatible API for TensorRT LLM triton backend

openwebrtc

A flexible cross-platform WebRTC client framework based on GStreamer

pjsip

PJSIP 2.x

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.