tommi/cri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Solving the Clive Wearing Problem: One-Shot Episodic Memory for Frozen Transformers

Browse Source 
Tommi Niemi / Rotko Networks

Hidden-state episodic memory for frozen transformers. No gradients.
Teach via one forward pass, recall via cosine similarity + logit injection.
200-line Python reproduction included.

pip install transformers torch numpy && python python/epimem.py
This commit is contained in:
Tommi Niemi
2026-04-05 01:20:17 +07:00
commit 176164815b
18 changed files with 786856 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
models/*.onnx
models/*.onnx.data