mirror of
https://github.com/alainnothere/llm-circuit-finder.git
synced 2026-07-05 15:52:13 +02:00
Initial commit
This commit is contained in:
commit
63911498e8
1 changed files with 2 additions and 0 deletions
2
README.md
Normal file
2
README.md
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
# llm-circuit-finder
|
||||
I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B improves logical deduction from 0.22→0.76 on BBH — no training, no weight changes, just routing hidden states through the same circuit twice. Tools included. Two AMD GPUs, one evening.
|
||||
Loading…
Add table
Add a link
Reference in a new issue