mazicwong

OSC8-Adoption

List of terminal emulators that support hyperlinks (OSC 8 escape sequences).

LLaVA-HR

LLaVA-HR: High-Resolution Large Language-Vision Assistant

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.

TinyLLaVA_Factory

A Framework of Small-scale Large Multimodal Models

pillow-simd

The friendly PIL fork

LLaVA-JP

LLaVA-JP is a Japanese VLM trained by LLaVA method

Long-CLIP

awesome-audio-plaza

Daily tracking of awesome audio papers, including music generation, zero-shot tts, asr, audio generation

rho

Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.

RapidLaTeXOCR

Formula recognition based on LaTeX-OCR and ONNXRuntime.

moviepy

Video editing with Python

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

shap

A game theoretic approach to explain the output of any machine learning model.

aider

aider is AI pair programming in your terminal

Awesome-Pruning

A curated list of neural network pruning resources.

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

GitHub-Chinese-Top-Charts

:cn: GitHub中文排行榜，各语言分设「软件 | 资料」榜单，精准定位中文好项目。各取所需，高效学习。

ALLaVA

Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model

InternVideo2

grok-1

Grok open release

Large-Audio-Models

Keep track of big models in audio domain, including speech, singing, music etc.

RepCodec

Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization

OpenWebMath

kenlm

KenLM: Faster and Smaller Language Model Queries

transformer-debugger

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Languagecodec

Language-Codec: Reducing the Gaps Between Discrete Codec Representation and Speech Language Models

Phi2-mini-Chinese

Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型，支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton