Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
thomascountz
19 days ago
|
parent
|
context
|
favorite
| on:
Good results fine tuning a local LLM like Qwen 3:0...
Yes, you can use constrained decoding like logit masking to force all invalid tokens in the vocabulary to -inf, and effectively be removed from selection. I believe llama.cpp exposes this by accepting a formatted grammar.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: