Pinned Repositories
Abstractive-Summarization-With-Transfer-Learning
Abstractive summarisation using Bert as encoder and Transformer Decoder
asterisk-k8s-demo
Demo of scalable Asterisk on Kubernetes
awesome-stacks
Deploy 90+ open-source web apps with one Docker command
docker-jitsi-meet
(EXPERIMENTAL) Jitsi Meet on Docker
fast-bert
Super easy library for BERT based NLP models
Guttenberg-Search
Open-source web app using Elasticsearch and Docker to search through the contents of 100 classic novels.
json-schema-builder
The JSON Schema form builder
kong-oidc-auth
OpenID Connect authentication with Kong gateway
Real-Time-Accent-Conversion
Real Time Foreign Accent Conversion
rogervaas's Repositories
rogervaas/AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
rogervaas/autolabel
Label, clean and enrich text datasets with LLMs.
rogervaas/clearflask
Listen to your users during product development with ClearFlask
rogervaas/DeepSeek-MoE
rogervaas/emailwiz
Script that installs/configures a Dovecot, Postfix, Spam Assassin, OpenDKIM Debian web server
rogervaas/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
rogervaas/guidance
A guidance language for controlling large language models.
rogervaas/incubator-answer
A Q&A platform software for teams at any scales. Whether it's a community forum, help center, or knowledge management platform, you can always count on Apache Answer.
rogervaas/instructor
openai function calls for humans
rogervaas/Js2Py
JavaScript to Python Translator & JavaScript interpreter written in 100% pure Python🚀 Try it online:
rogervaas/libpg_query
C library for accessing the PostgreSQL parser outside of the server environment
rogervaas/LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
rogervaas/LLM-Fine-Tuning
rogervaas/MC-SMoE
Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
rogervaas/mergekit
Tools for merging pretrained large language models.
rogervaas/MFTCoder
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs
rogervaas/mistral-src
Reference implementation of Mistral AI 7B v0.1 model.
rogervaas/mixtral
Mixtral finetuning
rogervaas/p2pcf
Low cost, low effort P2P WebRTC serverless signalling using Cloudflare Workers
rogervaas/pg_easy_replicate
Easily setup logical replication and switchover to new database with minimal downtime
rogervaas/pocketbase
Open Source realtime backend in 1 file
rogervaas/prometheus
[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score rubric, Prometheus is a good alternative for human evaluation and GPT-4 evaluation.
rogervaas/qa-lora
Pytorch code for paper QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
rogervaas/SER-datasets
A collection of datasets for the purpose of emotion recognition/detection in speech.
rogervaas/spear-tts-pytorch
Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch
rogervaas/SpeechTasks
This is a list of speech tasks and datasets, which can provide training data for Generative AI, AIGC, AI model training, intelligent speech tool development, and speech applications.
rogervaas/StreamDiffusion
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
rogervaas/StyleTTS2
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
rogervaas/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.
rogervaas/themis
Easy to use cryptographic framework for data protection: secure messaging with forward secrecy and secure data storage. Has unified APIs across 14 platforms.