A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
仓库
mgrankin 的仓库
mgrankin/minGPT-quantizeJupyter Notebook
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/nanoGPToctonionPython
nanoGPT with octonions
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/over9000Jupyter Notebook
Over9000 optimizer
(424 stars) (57 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/poetryPython
(2 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/porfirevichTypeScript
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/pytorch-vq-vaeJupyter Notebook
PyTorch implementation of VQ-VAE by Aäron van den Oord et al.
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/readmygenomePython
Claude skill for reading .genome bundles correctly, with provenance.
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/ru-gptsPython
Russian GPT2 models.
(4 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
Russian text quality plugin for Claude Code, Cowork, Codex CLI, Gemini CLI, Cursor, OpenClaw, and Notion — typography, info-style, editorial, UX writing
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/ruGPT-3.5-trainingJupyter Notebook
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/ru_transformersPython
(764 stars) (96 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/stihbotPython
telegram bot for Russian gpt models
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
Implementation of TabTransformer, attention network for tabular data, in Pytorch
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
Vector Quantization, in Pytorch
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)
mgrankin/yarnPython
YaRN: Efficient Context Window Extension of Large Language Models
(0 stars) (0 forks) (0 个已索引 issue) (0 个开放 good first issue)