darkshapes
/

MIR

@@ -46,19 +46,19 @@ Broad and general terms for system architectures.
 - `art` : Autoregressive transformer, typically LLMs
 - `lora`: Low-Rank Adapter (may work with dit or transformer)
 - `vae`: Variational Autoencoder
-etc
 ### Series
 Foundational network and technique types.
-### Compatability
 Implementation details based on version-breaking changes, configuration inconsistencies, or other conflicting indicators that have practical application.
 ### Goals
 - Standard identification scheme for **ALL** fields of ML-related development
 - Simplification of code for model-related logistics
 - Rapid retrieval of resources and metadata
-- Efficient and reliable compatability checks
 - Organized hyperparameter management
 > <details> <summary>Why not use `diffusion`/`sgm`, `ldm`/`text`/hf.co folder-structure/brand or trade name/preprint paper/development house/algorithm</summary>
@@ -72,7 +72,7 @@ Implementation details based on version-breaking changes, configuration inconsis
 > </details>
 > <details><summary>Why `unet`, `dit`, `lora` over alternatives</summary>
->
 > - UNET/DiT/Transformer are shared enough to be genre-ish but not too narrowly specific
 > - Very similar technical process on this level
 > - Functional and efficient for random lookups
@@ -80,10 +80,10 @@ Implementation details based on version-breaking changes, configuration inconsis
 > </details>
 > <details><summary>Roadmap</summary>
->
-> - Decide on `@` or `:` delimeters (like @8cfg for an indistinguishable 8 step lora that requires cfg)
 > - crucial spec element, or an optional, MIR app-determined feature?
-> - Proof of concept generative model registry
 > - Ensure compatability/integration/cross-pollenation with [OECD AI Classifications](https://oecd.ai/en/classification)
 > - Ensure compatability/integration/cross-pollenation with [NIST AI 200-1 NIST Trustworthy and Responsible AI](https://www.nist.gov/publications/ai-use-taxonomy-human-centered-approach)
 > </details>

 - `art` : Autoregressive transformer, typically LLMs
 - `lora`: Low-Rank Adapter (may work with dit or transformer)
 - `vae`: Variational Autoencoder
+- etc
 ### Series
 Foundational network and technique types.
+### Compatibility
 Implementation details based on version-breaking changes, configuration inconsistencies, or other conflicting indicators that have practical application.
 ### Goals
 - Standard identification scheme for **ALL** fields of ML-related development
 - Simplification of code for model-related logistics
 - Rapid retrieval of resources and metadata
+- Efficient and reliable compatibility checks
 - Organized hyperparameter management
 > <details> <summary>Why not use `diffusion`/`sgm`, `ldm`/`text`/hf.co folder-structure/brand or trade name/preprint paper/development house/algorithm</summary>
 > </details>
 > <details><summary>Why `unet`, `dit`, `lora` over alternatives</summary>
+>
 > - UNET/DiT/Transformer are shared enough to be genre-ish but not too narrowly specific
 > - Very similar technical process on this level
 > - Functional and efficient for random lookups
 > </details>
 > <details><summary>Roadmap</summary>
+>
+> - Decide on `@` or `:` delimiters (like @8cfg for an indistinguishable 8 step lora that requires cfg)
 > - crucial spec element, or an optional, MIR app-determined feature?
+> - Proof of concept generative model registry
 > - Ensure compatability/integration/cross-pollenation with [OECD AI Classifications](https://oecd.ai/en/classification)
 > - Ensure compatability/integration/cross-pollenation with [NIST AI 200-1 NIST Trustworthy and Responsible AI](https://www.nist.gov/publications/ai-use-taxonomy-human-centered-approach)
 > </details>