|
|
e13f973fd3
|
Rewrite paper to match code: only hidden-state storage + logit injection
|
2026-04-05 02:01:02 +07:00 |
|
|
|
b53e8278b2
|
Tighten abstract, restructure intro as The Clive Wearing Problem
|
2026-04-05 01:58:27 +07:00 |
|
|
|
8d90985814
|
Rename: Solving the Clive Wearing Problem
|
2026-04-05 01:54:49 +07:00 |
|
|
|
d619473190
|
epimem: One-shot gradient-free learning on frozen transformers
Tommi Niemi / Rotko Networks
- paper.md: full paper
- python/epimem.py: standalone Python reproduction
- export_onnx.py: ONNX export from HuggingFace
- results/memory_bank.json: example hidden-state vectors (896-dim)
- schema/: FlatBuffer schemas
Reproduce: pip install transformers torch && python python/epimem.py
(Downloads Qwen 2.5 0.5B automatically from HuggingFace)
|
2026-04-05 01:51:19 +07:00 |
|
|
|
404df92ade
|
epimem: One-shot gradient-free learning on frozen transformers
- paper.md: full paper (Tommi Niemi / Rotko Networks)
- python/epimem.py: standalone Python reproduction
- export_onnx.py: ONNX export from HuggingFace (generates model files)
- results/memory_bank.json: example hidden-state vectors (896-dim)
- schema/: FlatBuffer schemas for memory bank + organism
- models/tokenizer/: Qwen 2.5 tokenizer files
Run: pip install transformers torch && python python/epimem.py
(Downloads Qwen 2.5 automatically from HuggingFace)
|
2026-04-05 01:46:40 +07:00 |
|
|
|
c26496dacf
|
Initial: Clive Wearing paper + reproduction instructions
One-shot gradient-free learning on frozen transformers via
hidden-state episodic memory and sleep consolidation.
Tommi Niemi / Rotko Networks
|
2026-04-05 01:20:17 +07:00 |
|
