This is your work, valued
Full-Stack AI Engineer
vgae_pytorch. This repository implements variational graph auto encoder by Thomas Kipf.
★ 418EasyRLHF. EasyRLHF aims to provide an easy and minimal interface to train aligned language models, using off-the-shelf solutions and datasets
★ 9rasch_python. This repository implements Rasch model using Pytorch.
★ 6hidden_markov_model_python. A pure python implementation of Hidden Markov Model
★ 2GCC-caption-lora. This repo contains codes to train an image captioning model using GCC dataset.
★ 2bss_demand_prediction. Jupyter Notebook
★ 2moe_classifier. Does MoE work for classification head?
★ 1Korean-paraphrasing-seq2seq. Python
★ 1jenkins_test. jenkins testing
★ 1Reinforce-Paraphrase-Generation. This repository contains the data and code for the paper "An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation" (EMNLP2019). // Korean Paraphrase
★ 1anchor. Code for "High-Precision Model-Agnostic Explanations" paper
★ 1TransformerCVAE. Transformer-based Conditional Variational Autoencoder for Controllable Story Generation
★ 1snake_game. snake game with html5 canvas
★ 1progressive-generation. NAACL 2021 - Progressive Generation of Long Text
★ 1attention-learn-to-route. Attention based model for learning to solve different routing problems
★ 1MPL-pytorch. Unofficial PyTorch implementation of "Meta Pseudo Labels"
★ 1SimCTG. [NeurIPS'22] A Contrastive Framework for Neural Text Generation
★ 1DaehanKim.
★ 1trl. Train transformer language models with reinforcement learning.
★ 1lassl. Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets
★ 1story-gen-BART. Python
★ 1collaborative_filtering_python. This repository implements a Collaborative Filtering algorithm.
★ 1torchtext_tutorial. Simple tutorial on torchtext with polarity dataset
★ 1word_emb_for_txt_generation. Preprocess corpus and train word embeddings for text generation
★ 1DaehanKim.github.io. Build a Jekyll blog in minutes, without touching the command line.
★ 1math2kor. Convert math expression into Korean
★ 1projectEuler. solving arithmetic problems with python
★ 1citation_count_prediction. citation count prediction
★ 1kt_dataset. knowledge tracing datasets
★ 1reinforcement_learning_tutorial. Tutorials on Various reinforcement learning algorithm with Pytorch
★ 1ouroboros. Agent OS: Stop prompting. Start specifying.
★ 4.9kchrome-devtools-mcp. Chrome DevTools for coding agents
★ 47kslime. slime is an LLM post-training framework for RL Scaling.
★ 7.4kMoneyPrinterTurbo. 利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
★ 97kawesome-cursor-rules-mdc. Curated list of awesome Cursor Rules .mdc files
★ 3.6kopenai-cua-sample-app. Learn how to use CUA (our Computer Using Agent) via the API on multiple computer environments.
★ 1.7kpyCrossfade. pyCrossfade is the result of a personal project to use beat matching, gradual bpm shift on bars, and EQ modification to provide smooth and tunable transitions between music files.
★ 144Agentless. Agentless🐱: an agentless approach to automatically solve software development problems
★ 2.1kJanus. Janus-Series: Unified Multimodal Understanding and Generation Models
★ 18kphysics_of_skill_learning. We study toy models of skill learning.
★ 34LLaSA_training. LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
★ 662xcodec. AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
★ 308LLMInterviewQuestions. This repository contains LLM (Large language model) interview question asked in top companies like Google, Nvidia , Meta , Microsoft & fortune 500 companies.
★ 1.9kstreamlit-serverless. Run Streamlit Apps as serverless on AWS with HTTPS
★ 13abliterator. Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
★ 670evalverse. The Universe of Evaluation. All about the evaluation for LLMs.
★ 235uroman. Universal Romanizer that can convert any unicode script to roman (latin) script
★ 250LLaMA-O1. Large Reasoning Models
★ 803MLOps-Basics. Jupyter Notebook
★ 8.9kFG-transformer-TTS. Official implementation for the paper Fine-grained style control in transformer-based text-to-speech synthesis.
★ 90BigVGAN. Official PyTorch implementation of BigVGAN (ICLR 2023)
★ 1.2kStyleTTS-ZS. StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
★ 188super-monotonic-align. Python
★ 172g2pK. g2pK: g2p module for Korean
★ 270DMD2. (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
★ 1.4kml-mdm. Train high-quality text-to-image diffusion models in a data & compute efficient manner
★ 516DemoFusion. Let us democratise high-resolution generation! (CVPR 2024)
★ 2kSupercodec. Python
★ 51detail_tts. All generative model in one for better TTS model
★ 74Speech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
★ 18konediff. OneDiff: An out-of-the-box acceleration library for diffusion models.
★ 2kTTS-arxiv-daily. Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)
★ 659unet.cu. UNet diffusion model in pure CUDA
★ 661TransformerLens. A library for mechanistic interpretability of GPT-style language models
★ 3.7kmup. maximal update parametrization (µP)
★ 1.7kYaFSDP. YaFSDP: Yet another Fully Sharded Data Parallel
★ 990grokfast. Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
★ 583Samba. [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
★ 964OpenHands. 🙌 OpenHands: AI-Driven Development
★ 80kChatTTS. A generative speech model for daily dialogue.
★ 40kSimPO. [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
★ 955py-spy. Sampling profiler for Python programs
★ 15kzett. Code for Zero-Shot Tokenizer Transfer
★ 145iaf-vae. Pytorch Implementation of OpenAI's "Improved Variational Inference with Inverse Autoregressive Flow"
★ 84voice-vector. Deep neural networks for getting text-independent speaker embedding written in TensorFlow
★ 310AudioMNIST. Python
★ 374SpeechGPT. SpeechGPT Series: Speech Large Language Models
★ 1.4kiaf. Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"
★ 529FlashSpeech. ACM MM 2024 FlashSpeech: Efficient Zero-Shot Speech Synthesis
★ 155SpeechTokenizer. This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on
★ 659pyannote-core. Advanced data structures for handling temporal segments with attached labels.
★ 123pyvene. Stanford NLP Python library for understanding and improving PyTorch models via interventions
★ 891torchtitan. A PyTorch native platform for training generative AI models
★ 5.5kpykan. Kolmogorov Arnold Networks
★ 16kllama3. The official Meta Llama 3 GitHub site
★ 29kVAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
★ 8.7kschedule_free. Schedule-Free Optimization in PyTorch
★ 2.3kquant_py. 파이썬을 이용한 퀀트 투자 포트폴리오 만들기
★ 267koapy. KOAPY 는 키움 OpenAPI 를 Python 에서 쉽게 사용할 수 있도록 만든 라이브러리 패키지 및 툴입니다.
★ 222model-stock. Model Stock: All we need is just a few fine-tuned models
★ 129rerun. Visualize, query, and stream to train on multimodal robotics data.
★ 11khackathon. Python
★ 445unsloth. Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
★ 68kresource-stream. GPU programming related news and material links
★ 2.2ktransformer-debugger. Python
★ 4.1kEMO. [ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)
★ 129dataverse. The Universe of Data. All about data, data science, and data engineering
★ 563gemma_pytorch. The official PyTorch implementation of Google's Gemma models
★ 5.7kgemma. Gemma open-weight LLM library, from Google DeepMind
★ 5.5klag-llama. Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
★ 1.6kSPIN. The official implementation of Self-Play Fine-Tuning (SPIN)
★ 1.2knanotron. Minimalistic large language model 3D-parallelism training
★ 2.7kEAGLE. Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
★ 2.5klaserRMT. This is our own implementation of 'Layer Selective Rank Reduction'
★ 240OLMo. Modeling, training, eval, and inference code for OLMo
★ 6.6kHierSpeechpp. The official implementation of HierSpeech++
★ 1.2knlg-eval. Evaluation code for various unsupervised automated metrics for Natural Language Generation.
★ 1.4kcoco-caption. Jupyter Notebook
★ 1.2kbigcode-dataset. Jupyter Notebook
★ 497Entropy-ABF. Official implementation for 'Extending LLMs’ Context Window with 100 Samples'
★ 82Korpora. Korean corpus repository
★ 756InternVideo. [ECCV2024] Video Foundation Models & Data for Multimodal Understanding
★ 2.3kpheme. Python
★ 258Rank-N-Contrast. [NeurIPS 2023, Spotlight] Rank-N-Contrast: Learning Continuous Representations for Regression
★ 136OpenVoice. Instant voice cloning by MIT and MyShell. Audio foundation model.
★ 37kHALOs. A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
★ 908Resemblyzer. A python package to analyze and compare voices with deep learning
★ 3.3k42dot_LLM. 42dot LLM consists of a pre-trained language model, 42dot LLM-PLM, and a fine-tuned model, 42dot LLM-SFT, which is trained to respond to user prompts and supports both languages simultaneously by training a large amount of Korean and English text.
★ 133mergekit. Tools for merging pretrained large language models.
★ 7.2kml-ferret. Python
★ 8.7kagent-attention-pytorch. Implementation of Agent Attention in Pytorch
★ 93MahaTTS. Python
★ 275vec2text. utilities for decoding deep representations (like sentence embeddings) back to text
★ 1.1kmegablocks. Python
★ 1.6kMixtralKit. A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
★ 771auto-j. Generative Judge for Evaluating Alignment
★ 251intel-extension-for-transformers. ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
★ 2.2kelevenlabs-python. The official Python SDK for the ElevenLabs API.
★ 3kaudiocraft. 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.
★ 23kmamba. Mamba SSM architecture
★ 19kURIAL. Python
★ 316ml-engineering. Machine Learning Engineering Open Book
★ 18kattention_sinks. Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
★ 735distilabel. Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
★ 3.3kcyclical_annealing. OpenEdge ABL
★ 197LookaheadDecoding. [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
★ 1.3kUltraFastBERT. The repository for the code of the UltraFastBERT paper
★ 517StyleTTS2. StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
★ 6.3kvector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch
★ 4kwhisper_real_time. Real time transcription with OpenAI Whisper.
★ 2.9kvimGPT. Browse the web with GPT-4V and Vimium
★ 2.7kudlbook. Understanding Deep Learning - Simon J.D. Prince
★ 9.6kinsanely-fast-whisper. Jupyter Notebook
★ 13kgradnorm-pytorch. A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch
★ 132simplified_transformers. Python
★ 293BPO. Python
★ 336deeplake. Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
★ 9.2kWhispering-LLaMA. EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction
★ 271ttts. Train the next generation of TTS systems.
★ 169Eureka. Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)
★ 3.2ksilero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector
★ 9.6kCLUB. Code for ICML2020 paper - CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
★ 361realformer-pytorch. Implementation of RealFormer using pytorch
★ 101alignment-handbook. Robust recipes to align language models with human and AI preferences
★ 5.6kdenoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch
★ 11knaturalspeech2-pytorch. Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
★ 1.3kPython-Wrapper-for-World-Vocoder. A Python wrapper for the high-quality vocoder "World"
★ 789SpeechT5. Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
★ 1.4kgpt-engineer. CLI platform to experiment with codegen. Precursor to: https://lovable.dev
★ 55kTinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
★ 9kVALL-E-X. An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/
★ 7.9kmem0. Universal memory layer for AI Agents
★ 61klitgpt. 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
★ 13ksweep. Sweep: AI coding assistant for JetBrains
★ 7.7kmpire. A Python package for easy multiprocessing, but faster than multiprocessing
★ 2.1kQuIP. Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
★ 398whisper. Robust Speech Recognition via Large-Scale Weak Supervision
★ 105kFastSpeech2. An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
★ 2.2kfactool. FacTool: Factuality Detection in Generative AI
★ 934RetNet. An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"
★ 1.2ktortoise-tts. A multi-voice TTS system trained with an emphasis on quality
★ 15krelora. Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates
★ 474annoy. Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
★ 14kFastEdit. 🩹Editing large language models within 10 seconds⚡
★ 1.4kbark. 🔊 Text-Prompted Generative Audio Model
★ 39kxgen. Salesforce open-source LLMs with 8k sequence length.
★ 727OBELICS. Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.
★ 215Otter. 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
★ 3.4kNBCE. Naive Bayes-based Context Extension
★ 328AGIEval. Python
★ 774LOMO. LOMO: LOw-Memory Optimization
★ 994evolve-instruct. evolve llm training instruction, from english instruction to any language.
★ 120Program-of-Thoughts. Data and Code for Program of Thoughts [TMLR 2023]
★ 317composer. Supercharge Your Model Training
★ 5.5kOpenAlpaca. OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA
★ 304speculative-sampling. Simple implementation of Speculative Sampling in NumPy for GPT-2.
★ 99vdvae. Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"
★ 453ImageBind. ImageBind One Embedding Space to Bind Them All
★ 9.1kInternLM-techreport.
★ 895LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
★ 73kprm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems
★ 2.1kdatablations. Scaling Data-Constrained Language Models
★ 344KULLM. ☁️ 구름(KULLM): 고려대학교에서 개발한, 한국어에 특화된 LLM
★ 588Stable-Alignment. Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
★ 356DART. [ICLR 2022] Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
★ 131llm-foundry. LLM training code for Databricks foundation models
★ 4.4kqlora. QLoRA: Efficient Finetuning of Quantized LLMs
★ 11kPandaGPT. [TLLM'23] PandaGPT: One Model To Instruction-Follow Them All
★ 863AutoEvalGPT. Jupyter Notebook
★ 20KORani. Python
★ 108tree-of-thoughts. Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
★ 4.6kguidance. A guidance language for controlling large language models.
★ 22kpyllms. Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google, Groq, Reka, Together, AI21, Cohere, Aleph Alpha, HuggingfaceHub), with a built-in model performance benchmark.
★ 820llm-numbers. Numbers every LLM developer should know
★ 4.3kdeveloper. the first library to let you embed a developer agent in your own app!
★ 12kChatALL. Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火, 文心一言 and more, discover the best answers
★ 16kGPT-Bargaining. Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedback
★ 207UltraChat. Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
★ 2.9kHAE-RAE-BENCH. Benchmark in Korean Context
★ 138PaLM. An open-source implementation of Google's PaLM models
★ 820unlimiformer. Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"
★ 1.1kopen-korean-instructions. 언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.
★ 468jsonformer. A Bulletproof Way to Generate Structured JSON from Language Models
★ 4.9krecurrent-memory-transformer-pytorch. Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch
★ 424RedPajama-Data. The RedPajama-Data repository contains code for preparing large datasets for training large language models.
★ 5kpandas-ai. Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
★ 24kadapters. A Unified Library for Parameter-Efficient and Modular Transfer Learning
★ 2.8kflan-ul2-alpaca. Python
★ 33gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
★ 77kreward-modeling. Python
★ 98GPTeacher. A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer
★ 1.7kbabyagi. Python
★ 22kEasyLM. Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
★ 2.5kAI-Functions. AI-Powered Function Magic: Never code again with GPT models!
★ 936basaran. Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
★ 1.3kself-refine. LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
★ 811RRHF. [NIPS2023] RRHF & Wombat
★ 806FasterTransformer. Transformer related optimization, including BERT, GPT
★ 6.4knatural-instructions. Expanding natural instructions
★ 1kChatGPT-CodeReview. 🐥 A code review bot powered by ChatGPT
★ 4.5k