|
|
--- |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
massive thank you to [@silveroxides](https://huggingface.co/silveroxides) for phenomenal work collecting pristine state dicts and related information |
|
|
|
|
|
# |
|
|
|
|
|
# MIR (Machine Intelligence Resource) |
|
|
# |
|
|
is a naming standard, a schema for ML work.<br> |
|
|
In its current incarnation, it looks like this: |
|
|
|
|
|
|
|
|
## mir:transformer.clip-l.stable-diffusion-xl-base |
|
|
``` |
|
|
domain:[architecture].[implementation].[compatability] |
|
|
``` |
|
|
|
|
|
It is formed from a combination the original work from CivitAi [AIR-URN](https://github.com/civitai/civitai/wiki/AIR-%E2%80%90-Uniform-Resource-Names-for-AI) project<br> |
|
|
and the super-resolution registry code from the [Spandrel](https://github.com/chaiNNer-org/spandrel/blob/main/libs/spandrel/spandrel/__helpers/registry.py) library. |
|
|
|
|
|
## Goals |
|
|
- Standard identification scheme for all ML-related development |
|
|
- Simplification of code for model-related logistics |
|
|
- Rapid retrieval of resources and metadata |
|
|
- Efficient and reliable compatability checks |
|
|
- Hyperparameter management |
|
|
|
