Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
worstspotgain
on June 7, 2024
|
parent
|
context
|
favorite
| on:
Dragonfly: A large vision-language model with mult...
It's just an artifact of the training sample pairs IMO. You can reduce it by fine-tuning the prompt, or even LoRA if you'd like to nuke this mosquito.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: