Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nl
3 months ago
|
parent
|
context
|
favorite
| on:
Ask HN: Has anyone replaced Claude/GPT with a loca...
Qwen 3.5 and above use Gated DeltaNet which alternate attention and SSM layers:
https://sebastianraschka.com/llms-from-scratch/ch04/08_delta...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://sebastianraschka.com/llms-from-scratch/ch04/08_delta...