Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
HarHarVeryFunny
on Jan 3, 2025
|
parent
|
context
|
favorite
| on:
Coconut by Meta AI – Better LLM Reasoning with Cha...
But we're discussing a
training
technique, that explicitly takes advantage of the continuous (and embedding vs token probability) representations ...
You could quantize a model like this after training, as usual, but that's irrelevant.
astrange
on Jan 4, 2025
[–]
The paper title is "Training Large Language Models to Reason in a Continuous Latent Space". It's true it says training in the title, but the goal (reasoning in continuous space) happens at inference time.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
You could quantize a model like this after training, as usual, but that's irrelevant.