Skip to main content

CortexNet: unified neural network architecture beyond Transformers

Project description

CortexNet

CI PyPI version License

CortexNet 是一个面向语言建模与推理场景的神经网络架构实现,核心思路是将多尺度状态空间建模、选择性稀疏注意力、记忆系统、条件路由与可选高级推理模块组合到同一框架中。

本仓库已经完成以下整理:

  • 统一对外主模型命名为 CortexNet(不再以 *V3 作为主入口)
  • 代码按 pip 可发布标准重构到 cortexnet/ 包目录
  • 基准/聊天/评测脚本统一归档到 scripts/
  • 清理无用导入、冗余变量和缓存文件
  • 补充架构文档和模块映射文档,方便开源协作

Installation

pip install -e .

或构建并安装 wheel:

python -m pip install build
python -m build
pip install dist/*.whl

CLI

python -m cortexnet --version
python -m cortexnet --smoke-test

Quick Start

import torch
from cortexnet import CortexNet, CortexNetConfig

config = CortexNetConfig(
    vocab_size=32000,
    hidden_size=512,
    num_layers=4,
    num_heads=8,
    max_seq_len=2048,
)

model = CortexNet(config).eval()
input_ids = torch.randint(0, config.vocab_size, (1, 16))

with torch.no_grad():
    out = model(input_ids)
print(out["logits"].shape)

Package Layout

cortexnet/
  adapter/      # 开源模型识别、权重映射、架构适配、推理适配、校准
  ops/          # 设备与算子抽象(CPU/CUDA/MPS/NPU/MLU)
  model.py      # 主模型与 from_pretrained
  blocks.py     # 核心 block 组合
  ...
scripts/
  benchmarks/   # 性能与量化基准
  chat/         # 聊天脚本
  eval/         # 能力评测脚本
  dev/          # 一键流程与测试运行器
tests/          # 回归与单元测试

Test

python -m pytest -q

Docs

  • 文档中心(中英文完整文档):docs/README.md
  • 架构说明:ARCHITECTURE.md
  • 模块职责图:MODULE_MAP.md
  • 变更记录:CHANGELOG.md
  • 贡献指南:CONTRIBUTING.md
  • 支持与问题分流:SUPPORT.md
  • 安全策略:SECURITY.md
  • 示例代码:examples/README.md

Compatibility Notes

  • 对外推荐只使用 CortexNet
  • 历史命名(如 CortexNetV2 / CortexNetV3)仍保留为兼容别名,避免旧代码立即失效。

Development Commands

make install-dev
make lint
make test-all
make check

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cortexnet-3.2.3.tar.gz (116.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cortexnet-3.2.3-py3-none-any.whl (126.6 kB view details)

Uploaded Python 3

File details

Details for the file cortexnet-3.2.3.tar.gz.

File metadata

  • Download URL: cortexnet-3.2.3.tar.gz
  • Upload date:
  • Size: 116.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for cortexnet-3.2.3.tar.gz
Algorithm Hash digest
SHA256 212bab1f4a05b834037fce80108defe72a987b11f0186dc7681e9f21c65b45bb
MD5 f395dad0d5f343d53dbe0a42933f6435
BLAKE2b-256 8c16b59e0ff8482eddf3f22de2232cc03c7d7df895a437ddbd5849669e2c1797

See more details on using hashes here.

File details

Details for the file cortexnet-3.2.3-py3-none-any.whl.

File metadata

  • Download URL: cortexnet-3.2.3-py3-none-any.whl
  • Upload date:
  • Size: 126.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for cortexnet-3.2.3-py3-none-any.whl
Algorithm Hash digest
SHA256 478b5c9ea5e2ac715c5551cd7587b0c46cade7a3f9fb6c7fd240c7333c855495
MD5 a43be2dc1a19d1baed02c0bf66fb4667
BLAKE2b-256 07f3c5dfc33dab2440bf62e1adef37fd61718bd6e6f5f45fa21faf9493449d1a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page