Lion (EvoLved Sign Momentum) optimizer utilizing sign operations for memory-efficient uniform gradient updates.
Lion (EvoLved Sign Momentum) optimizer utilizing sign operations for memory-efficient uniform gradient updates.
Lookahead optimizer wrapper stabilizing optimization trajectories by interpolating fast and slow weights every k steps.
Lookahead optimizer wrapper stabilizing optimization trajectories by interpolating fast and slow weights every k steps.
Global L2 norm adaptive gradient clipping engine to mitigate exploding gradients during deep neural network training.
Global L2 norm adaptive gradient clipping engine to mitigate exploding gradients during deep neural network training.
SGDR: Stochastic Gradient Descent with Warm Restarts and Cosine Annealing learning rate schedule engine.
SGDR: Stochastic Gradient Descent with Warm Restarts and Cosine Annealing learning rate schedule engine.
AdamW optimizer engine decoupling L2 weight decay regularization from adaptive gradient first and second moments.
AdamW optimizer engine decoupling L2 weight decay regularization from adaptive gradient first and second moments.
让 AI 用你的数据生成科研图表：108 个配方，鲜艳与稳重两种风格，多套配色，交付图片与源码。仅限个人非商业使用。
On-device audio transcription toolkit - trim, tag, transcribe and export recordings locally, with a Python engine and an Android demo app.
Scale-Vector Alignment (SVA): scale-aware morphological similarity for multiscale astronomical intensity fields using Constrained Diffusion Decomposition
PRINTFILM：AI 科普视频与漫剧创作平台
Awesome paper list for reasoning generalization in LLMs.
⚡ Zero-reload dynamic AI model switcher & local proxy for VSCode Copilot Chat via 9Router
This repo will showing how progressively can develope Generative AI as AI engineer from beginner
Poseidon algebraic sponge hash function optimized for zero-knowledge arithmetic circuits with MDS matrix diffusion and power S-boxes.
Poseidon algebraic sponge hash function optimized for zero-knowledge arithmetic circuits with MDS matrix diffusion and power S-boxes.
Python reference implementation for finite-volume neutron-diffusion calculations on regular hex-z lattices
🔥 企业级 OpenAI / ChatGPT Plus、Pro (5x/20x)、Team 官方合规代采平台。支持企业银行公对公转账、开具 6% 增值税专用发票、签署加盖公章 SLA 兜底协议。商务微信：yqtp01
Fine-tuning BERT (bert-base-uncased) for SMS spam/ham classification, benchmarked against a Naive Bayes baseline and BERT as a frozen feature extractor on the same test set. Includ...
LLMs → Prompting → Structured Outputs → Embeddings → Vector Databases → RAG → Fine-Tuning → Multimodal AI → Agents → Evaluation → Security → APIs → Production Deployment
Python → ML → Deep Learning → LLMs → RAG → Agents → MCP → APIs → Evaluation → Security → Deployment → Enterprise AI