Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
_flux
3 months ago
|
parent
|
context
|
favorite
| on:
Vision language models are blind
Why do you think it's probable? The much smaller llava that I can run in my consumer GPU can also do "OCR", yet I don't believe anyone has hidden any OCR engine inside llama.cpp.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: