This release is a pre-release and may not be stable for production use.
MB-8: Mathematical Brain 8-Level Architecture
MB-8 — full-training library for a novel 8-level neural architecture combining SSM, Hopfield networks, working memory, predictive coding, and plasticity mechanisms.
Features
- 8 architectural levels: Membrane → Synapse → Dendrites → SSM → Hopfield/Phase → Working Memory → Error → Plasticity/Consolidation
- Multiple model variants: SingleStream, DualStream, MB8ForCausalLM (full 8-level)
- Training modes: Pretrain (CLM), SFT (chat-style), GRPO (RL)
- Notebook API: Transformers-style
Trainer+TrainingArgumentsfor Jupyter/Colab - CLI tools:
mb8-train,mb8-sft,mb8-grpo,mb8-eval,mb8-inspect - Epistemic framework: Hypothesis-driven development with go/no-go criteria
Quickstart
from mb8 import MB8Config, MB8ForCausalLM, TrainingArguments, Trainer
model = MB8ForCausalLM(MB8Config.from_preset("tiny_10m"))
trainer = Trainer(
model=model,
args=TrainingArguments(output_dir="outputs", max_steps=100),
train_dataset=...,
)
trainer.train()
Installation
pip install mb8
Documentation
See api-docs/ for full reference and quickstart guide.
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for mb8 0.1.1b1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mb8-0.1.1b1.tar.gz | 77.1 kB | Without provenance | Details for mb8-0.1.1b1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mb8-0.1.1b1-py3-none-any.whl | Python 3 | none | any | Details for mb8-0.1.1b1-py3-none-any.whl |
Total release size: 177.6 kB
Release files / mb8-0.1.1b1.tar.gz
| Download URL | mb8-0.1.1b1.tar.gz |
|---|---|
| Size | 77.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1fdbcd221605b5bc3fcaa22ab3232fcb8f914268ba4627c1a18abf1ac9584332
|
|
BLAKE2b-256 checksum How to use checksums |
bf2c5a05343e1fe05970c60974271d5beec073ad99ce06d8417fa26ed6625b36
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.26 {"installer":{"name":"uv","version":"0.11.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / mb8-0.1.1b1-py3-none-any.whl
| Download URL | mb8-0.1.1b1-py3-none-any.whl |
|---|---|
| Size | 100.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5cc16a1d2b73612607bf927c5aa467351aae3d114efc0f7f407f16ab728067a0
|
|
BLAKE2b-256 checksum How to use checksums |
8698d7249bee5c4e1ce8d67c96ea5eaea07a1dbdc3b232d1f996aadb0b77061b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.11.26 {"installer":{"name":"uv","version":"0.11.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for mb8 0.1.1b1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
