SUMMARY AI要約 by gpt-5-mini
A from‑scratch implementation of a GPT-style transformer built while completing the NeetCode ML course (author: Kartik Singh, May 5, 2026). Intended for learners and engineers who want a hands‑on, educational reimplementation of transformer/GPT internals and training pipeline. What it is for: - End‑to‑end learning and experimentation: primitives, attention, transformer blocks, training and generation. Who uses it: - Students, ML practitioners, and researchers studying transformer internals or implementing lightweight GPT variants. Key features: - Model: self‑attention head, multi‑head attention, transformer blocks, GPT model, grouped query attention, KV cache for fast inference. - Normalization variants: layer, batch, RMS. - Embeddings, positional encoding. - Data pipeline: BPE tokenizer, vocab, dataset loader, preprocessing. - Foundations: neurons, backprop, MLPs, activations, losses, training loop implemented from scratch. - Scripts: train.py and generate.py; quick start via requirements and these scripts.
使用言語(バイト数比)
オーナー情報
日付
| GitHub作成日 | 2026-05-05 |
| 最終Push | 2026-05-09 |
| 当サイト初検出 | 2026-05-09 |
| 最終取得 | 2026-05-09 18:11 |
類似Repo (同じ言語のAI関連Repo)
Reverse proxy for your ai quota from the SW platform.
dea6cat/2b-agentThis llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus
Zuboy/Carbon-Cost-Optimizer-Agentic-AIAn AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.
FuchaZ/lm-studio-vision-bridge给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务
Shrutirowlo/AI-Video-AgentAI-powered video generation agent that automates script analysis, scene planning, and video creation.
Shivang0/social-visionPaste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.
markusbegerow/claude-fuer-oeffentliche-verwaltung⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.
knowledgegut/course-distiller把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF；最後的重組交還人腦。A Claude Code skill by 知識包小腸.