hkchengrex/Cutie
[arXiv 2023] Putting the Object Back Into Video Object Segmentation
Language: Python
#computer_vision #deep_learning #pytorch #segmentation #video_editing #video_object_segmentation #video_segmentation
Stars: 123 Issues: 1 Forks: 12
https://github.com/hkchengrex/Cutie

netease-youdao/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
Language: Python
#ai #deep_learning #emotion #emotivoice #multi_speaker #prompt #python #pytorch #speech #speech_synthesis #style #text_to_speech #tts
Stars: 432 Issues: 3 Forks: 38
https://github.com/netease-youdao/EmotiVoice

kyegomez/MultiModalMamba
A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.
Language: Python
#ai #artificial_intelligence #attention_mechanism #machine_learning #mamba #ml #pytorch #ssm #torch #transformer_architecture #transformers #zeta
Stars: 264 Issues: 0 Forks: 9
https://github.com/kyegomez/MultiModalMamba

apple/ml-aim
This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Models
Language: Python
#jax #large_scale_vision_models #mlx #pytorch
Stars: 181 Issues: 1 Forks: 8
https://github.com/apple/ml-aim

google/gemma_pytorch
The official PyTorch implementation of Google's Gemma models
Language: Python
#gemma #google #pytorch
Stars: 1126 Issues: 4 Forks: 53
https://github.com/google/gemma_pytorch

PaulPauls/llama3_interpretability_sae
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Language: Python
#feature_extraction #feature_steering #llama3 #llm_interpretability #open_research #pytorch #sparse_autoencoder
Stars: 285 Issues: 0 Forks: 13
https://github.com/PaulPauls/llama3_interpretability_sae

zhihu/ZhiLight
A highly optimized inference acceleration engine for Llama and its variants.
Language: C++
#cpm #cuda #gpt #inference_engine #llama #llm #llm_serving #minicpm #pytorch #qwen
Stars: 192 Issues: 1 Forks: 16
https://github.com/zhihu/ZhiLight

facebookresearch/large_concept_model
Large Concept Models: Language modeling in a sentence representation space
Language: Python
#language_models #nlp #pytorch #seq2seq #sequence_to_sequence
Stars: 340 Issues: 0 Forks: 27
https://github.com/facebookresearch/large_concept_model

MoonshotAI/MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
Language: Python
#flash_attention #llm #llm_serving #llm_training #moe #pytorch #transformer
Stars: 521 Issues: 2 Forks: 16
https://github.com/MoonshotAI/MoBA

babycommando/neuralgraffiti
Live-bending a foundation model’s output at neural network level.
Language: Jupyter Notebook
#finetuning #liquid_neural_networks #llm #neural_network #pytorch #self_attention #transformers
Stars: 217 Issues: 0 Forks: 16
https://github.com/babycommando/neuralgraffiti

FunAudioLLM/Fun-ASR
Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
Language: Python
#audio #audio_language_model #audio_understanding #fun_asr #multimodal_large_language_models #pytorch #speaker_diarization #speech_recognition
Stars: 264 Issues: 4 Forks: 8
https://github.com/FunAudioLLM/Fun-ASR

duoan/TorchCode
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
Language: Jupyter Notebook
#interview #leetcode #pytorch
Stars: 640 Issues: 3 Forks: 22
https://github.com/duoan/TorchCode

RightNow-AI/autokernel
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
Language: Python
#autoresearch #cuda #gpu #kernel_optimization #pytorch #triton
Stars: 602 Issues: 4 Forks: 45
https://github.com/RightNow-AI/autokernel

kyegomez/OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Language: Python
#ai #anthropic #attention #claude #claude_ai #claude_code #claude_code_plugin #claude_mythos #claude_sonnet #deepmind #gpt_5 #gpt_7 #jax #looped_transformers #ml #pytorch #sonnet #torch
Stars: 2024 Issues: 7 Forks: 373
https://github.com/kyegomez/OpenMythos

raiyanyahya/how-to-train-your-gpt
Build a modern LLM from scratch. Every line commented. Explained like we are five.
Language: Jupyter Notebook
#attention_mechanism #deep_learning #educational #from_scratch #gpt #language_model #llama #llm #machine_learning #natural_language_processing #python #pytorch #tokenisation #transformers #tutorial
Stars: 478 Issues: 0 Forks: 63
https://github.com/raiyanyahya/how-to-train-your-gpt