Update README.md

README.md

@@ -5,7 +5,12 @@ datasets:
 metrics:
 - mse
 ---
-# Translators Layout
+# Translator models for Make it SING (https://huggingface.co/papers/2603.14610)
+Their purpose is to translate the penultimate layer of a a classifier to the image embedding space of CLIP.
+In this repo they currently support (https://huggingface.co/kakaobrain/karlo-v1-alpha) variation but can easily retrained to any other.
+All these models were trained on MSE loss via ridge regression with scikit-learn library and then migrated to PyTorch. 
+
+## Translators Layout
 
 Expected structure:
 
@@ -22,7 +27,7 @@ translators/
       best.pt
 ```
 
-Required metadata fields:
+## Required metadata fields:
 - `model_name`
 - `translator_name`
 - `architecture`
@@ -32,7 +37,7 @@ Required metadata fields:
 - `hidden_dim` (optional; positive integer; defaults to `in_dim`)
 - `checkpoint_file` (relative path only; no absolute paths or `..`)
 
-Validation notes:
+## Validation notes:
 - Metadata schema is strict: unknown keys are rejected.
 - `model_name` and `translator_name` inside `metadata.yaml` must match their directory names.
 - `architecture` supported are one of: `linear`, `3layer`, `4layer`, `residual`.