exdysa commited on
Commit
7adc8e8
·
verified ·
1 Parent(s): 6ba66a1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -12
README.md CHANGED
@@ -6,30 +6,31 @@ language:
6
  massive thank you to [@silveroxides](https://huggingface.co/silveroxides) for phenomenal work collecting pristine state dicts and related information
7
 
8
  #
 
 
9
 
10
- # MIR (Machine Intelligence Resource)
11
- #
12
  MIR is a naming standard, a proposed schema for ML work.<br>
13
  In its current incarnation, it looks like this:
14
 
15
- #
16
- ## mir : model . transformer . clip-l : stable-diffusion-xl
17
- #
18
- ```
19
- mir : model . lora . hyper : flux-1
20
- ^ ^ ^ ^ ^
21
- mir:[domain].[architecture].[implementation]:[compatibility]
 
22
  ```
23
 
24
 
25
- It is inspired by the original work from CivitAi [AIR-URN](https://github.com/civitai/civitai/wiki/AIR-%E2%80%90-Uniform-Resource-Names-for-AI) project<br>
26
- and the super-resolution registry code from [Spandrel](https://github.com/chaiNNer-org/spandrel/blob/main/libs/spandrel/spandrel/__helpers/registry.py) library.
27
 
28
  ## Goals
29
  - Standard identification scheme for all ML-related development
30
  - Simplification of code for model-related logistics
31
  - Rapid retrieval of resources and metadata
32
  - Efficient and reliable compatability checks
33
- - Hyperparameter management
34
 
35
 
 
6
  massive thank you to [@silveroxides](https://huggingface.co/silveroxides) for phenomenal work collecting pristine state dicts and related information
7
 
8
  #
9
+ > [!IMPORTANT]
10
+ > # MIR (Machine Intelligence Resource)
11
 
 
 
12
  MIR is a naming standard, a proposed schema for ML work.<br>
13
  In its current incarnation, it looks like this:
14
 
15
+ > [!NOTE]
16
+ > # mir : model . transformer . clip-l : stable-diffusion-xl
17
+
18
+
19
+ ```
20
+ mir : model . lora . hyper : flux-1
21
+ ↑ ↑ ↑ ↑ ↑
22
+ mir:[domain].[architecture].[implementation]:[compatibility]
23
  ```
24
 
25
 
26
+ This work is inspired by the AIR standard from CivitAi [AIR-URN](https://github.com/civitai/civitai/wiki/AIR-%E2%80%90-Uniform-Resource-Names-for-AI) project<br>
27
+ and by the super-resolution registry code from [Spandrel](https://github.com/chaiNNer-org/spandrel/blob/main/libs/spandrel/spandrel/__helpers/registry.py) library.
28
 
29
  ## Goals
30
  - Standard identification scheme for all ML-related development
31
  - Simplification of code for model-related logistics
32
  - Rapid retrieval of resources and metadata
33
  - Efficient and reliable compatability checks
34
+ - Organized hyperparameter management
35
 
36