mhc 上下文优化
- 作者仓库星标 39
- 作者仓库 awesome-omni-skill
mHC Skill
Manifold-Constrained Hyper-Connections (mHC) uses Doubly Stochastic Matrices to improve Deep Learning stability.
Contents
- Examples
- Full JAX implementation of
sinkhorn_knoppandmhc_layer_forward.
- Full JAX implementation of
- Deep Theory
- Motivation, stability proofs, and scalability arguments.
Usage
Use this skill when implementing Deep Transformers (1000+ layers) where standard residual connections fail (Gradient Vanishing, Representation Collapse).
# Quick Ref: Sinkhorn-Knopp (See examples.md for full context)
def sinkhorn_knopp(log_matrix, n_iters=20):
M = jnp.exp(log_matrix)
def body(i, m):
m /= m.sum(axis=1, keepdims=True)
m /= m.sum(axis=0, keepdims=True)
return m
return jax.lax.fori_loop(0, n_iters, body, M)- 流狐分类
- AI 智能
- 作者声明 Agent
- 未找到明确声明；不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描，不代表运行安全
- 作者 / 版本 / 许可
- @diegosouzapw · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 即装即用
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- Python
- 检测到的文件与系统行为
-
- 只读
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无（仅作为资料）
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。 Contents
Examples Full JAX implementation of sinkhornknopp and mhclayerforward. Deep Theory
Usage
Use this skill when implementing Deep Transformers (1000+ layers) where standard residual connections fail (Gradient Vanishing, Representation Collapse).
# mHC Skill
Manifold-Constrained Hyper-Connections (mHC) uses Doubly Stochastic Matrices to improve Deep Learning stability.
## Contents
- [Examples](examples.md)
- Full JAX implementation of `sinkhorn_knopp` and `mhc_layer_forward`.
- [Deep Theory](reference.md)
- Motivation, stability proofs, and scalability arguments.
## Usage
Use this skill when implementing Deep Transformers (1000+ layers) where standard residual connections fail (Gradient Vanishing, Representation Collapse).
```python
# Quick Ref: Sinkhorn-Knopp (See examples.md for full context)
def sinkhorn_knopp(log_matrix, n_iters=20):
M = jnp.exp(log_matrix)
def body(i, m):
m /= m.sum(axis=1, keepdims=True)
m /= m.sum(axis=0, keepdims=True)
return m
return jax.lax.fori_loop(0, n_iters, body, M)
``` 证据边界与执行链路
作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。
章节 -> Contents → Usage
要点 -> Manifold-Constrained Hyper-Connections (mHC) uses Doubly Stochastic Matrices to improve Deep Learning stability. · - [Examples](examples.md) - Full JAX implementation of sinkhornknopp and mhclayerforward.
文件/命令 -> sinkhornknopp · mhclayerforward · examples.md · reference.md
内容 SHA-256 -> 527c6edee267
原文结构
适用与边界
原文中的明确线索
sinkhornknopp、mhclayerforward、examples.md、reference.md