add readme

README.md

@@ -0,0 +1,28 @@
+---
+library_name: transformers
+tags:
+  - custom_generate
+---
+
+## Description
+Implementation of the cache introduced in the [Attention Sinks paper](https://arxiv.org/abs/2309.17453). It allows the
+model to generate beyond the length of its context window, without losing fluency in the conversation. As it discards
+past tokens, the model will lose the ability to generate tokens that depend on the context that was discarded.
+
+This implementation should match the `SinkCache` class present in `transformers<4.53.0`.
+
+![Sink Cache diagram from the original paper](https://arxiv.org/html/2309.17453v4/x1.png)
+
+## Base model:
+
+
+## Model compatibility
+
+
+## Additional Arguments
+
+
+## Output Type changes
+
+
+## Example usage