deep-learning

easy-bert是一个中文NLP工具，提供诸多bert变体调用和调参方法，极速上手；清晰的设计和代码注释，也很适合学习

Emotions recognition from audio and text files (only russian language)

[NeurIPS 2023] This is the official code for the paper "TPSR: Transformer-based Planning for Symbolic Regression"

Implementation of N-Grammer, augmenting Transformers with latent n-grams, in Pytorch

Implementation of the proposed MaskBit from Bytedance AI

MLOps - Deploy models at scale, Generative AI - Build applications with LLMs, NLP - Understand Transformers & Text Generation Models, Computer Vision - Build GANs projects like Deepfakes, ML System Design, hands-on project building and code algorithms from scratch.

A self-supervised foundation ECG model for broad and scalable cardiac applications

《SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks》Speech processing with prompting paradigm

VerifAI initiative to build open-source easy-to-deploy generative question-answering engine that can reference and verify answers for correctness (using posteriori model)

Material for lectures on Diffusion models at IE university

🤖 language modeling sft demos

Generative AI Pharmacist (For Demo Purposes Only)

Official repo for Recursion's accepted spotlight paper at NeurIPS 2023 Generative AI & Biology workshop.

Transformer-powered hashtag segmentation with beam search, RRF ensembles, and agent-ready MCP workflows. A scalable alternative to heuristic splitters and massive LLMs.

Solutions for CS224n (2022)

Multi-Agent Blog Generator based on Agno framework. Supports leading LLM providers like OpenAI, Gemini, Claude, and Grok.

The largest multilingual image-text classification dataset. It contains fashion products.

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

Zero-Shot Text-to-Image Generation VQGAN+CLIP Dockerized