nivibilla

PragitiPath_AI

PragatiPath AI is an innovative video platform that leverages real-time hand gesture recognition to enhance educational engagement. Using OpenCV and MediaPipe, it interprets hand gestures for interactive content illustration, including drawing, erasing, and changing colors.

AnyGPT

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

chatbot-ui

AI chat for every model.

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

functionary

Chat language model that can use tools and interpret the results

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

iTransformer

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group

CALM-pytorch

Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind

dolphin-system-messages

Dolphin System Messages

jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

crewAI

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

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

qmoe

Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".

multi_token

Embed arbitrary modalities (images, audio, documents, etc) into large language models.

ADOP

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

hydra-moe

NeRFocus

Extending Mip-NeRF for rendering defocus effects

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

vits_chinese

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

speech-adapters

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

PEL-TTS

NaturalSpeech2

NaturalSpeech2

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

efficient-vits-finetuning

Finetuning VITS Efficiently

naturalspeech

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

BlockTheSpot

Video, audio & banner adblock/skip for Spotify. This project has been superceded by SpotX: https://github.com/SpotX-CLI/SpotX-Win