Hugging Face's logo

transformers-community
/
sink_cache

Transformers
Safetensors
custom_generate
Model card Files
xet
 Community
joaogante commited on
Commit
2a0ad2b
·
1 Parent(s): 835a8a6

add WIP

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -4,6 +4,8 @@ tags:
4
  - custom_generate
5
  ---
6
 
 
 
7
  ## Description
8
  Implementation of the cache introduced in the [Attention Sinks paper](https://arxiv.org/abs/2309.17453). It allows the
9
  model to generate beyond the length of its context window, without losing fluency in the conversation. As it discards
 
4
  - custom_generate
5
  ---
6
 
7
+ ⚠️ WORK IN PROGRESS ⚠️
8
+
9
  ## Description
10
  Implementation of the cache introduced in the [Attention Sinks paper](https://arxiv.org/abs/2309.17453). It allows the
11
  model to generate beyond the length of its context window, without losing fluency in the conversation. As it discards