mhc
- Repo stars 39
- Author repo awesome-omni-skill
- Domain
- AI
- Author-declared agents
- No explicit declaration found; this is not inferred or tested compatibility
- Static check
- 88 / 100 · heuristic scan, not runtime safety proof
- Runtime evidence
- Not run; no isolated runtime test evidence is currently recorded
- Author / version / license
- @diegosouzapw · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Detected file/system behavior
-
- Read-only
- Network behavior
- Local-only
- Install commands
- None (reference only)
Heads up: Tool permissions are not declared; actual access depends on the runtime.
# 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)
```
Sections and files
Listed in source order.
sections -> Contents → Usage
terms -> Manifold-Constrained Hyper-Connections (mHC) uses Doubly Stochastic Matrices to improve Deep Learning stability. · - [Examples](examples.md) - Full JAX implementation of sinkhornknopp and mhclayerforward.
files/cmd -> sinkhorn_knopp · mhc_layer_forward · examples.md · reference.md
body sha256 -> 527c6edee267
Contents
Examples Full JAX implementation of
sinkhorn_knoppandmhc_layer_forward. 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).