Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
doctorpangloss
on May 28, 2024
|
parent
|
context
|
favorite
| on:
Llama 3-V: Matching GPT4-V with a 100x smaller mod...
Shouldn't CogAgent be in this comparison?
m00x
on May 28, 2024
[–]
CogVLM should be, not sure how CogAgent plays into this. This isn't an agent.
doctorpangloss
on May 28, 2024
|
parent
[–]
You would use CogAgent in VQA mode. Why would someone downvote suggesting to test one of the most powerful multimodal LLMs? Because it doesn't have "V" in its name? CogAgent is improved on many tasks compared to CogVLM.
m00x
on May 29, 2024
|
root
|
parent
[–]
I didn't downvote, only replied.
CogAgent is also CogVLM modified to handle documents and larger images. CogVLM is better for VQA.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: