[HN Gopher] Dragonfly: A large vision-language model with multi-...
___________________________________________________________________
Dragonfly: A large vision-language model with multi-resolution zoom
Author : jasondavies
Score : 78 points
Date : 2024-06-06 18:31 UTC (4 hours ago)
(HTM) web link (www.together.ai)
(TXT) w3m dump (www.together.ai)
| ilaksh wrote:
| I have been testing out LLMs with the together.ai API, but I
| can't figure out how to use the multimodal models with the API. I
| don't see any in their model list.
| GaggiX wrote:
| Is there a demo or API to test the model? There are so many
| vision language models these days, it's hard to say which one is
| better, they also use in many cases different benchmarks.
| alexey-salmin wrote:
| Huggingface links are in the article
| https://huggingface.co/togethercomputer/Llama-3-8B-Dragonfly...
| GaggiX wrote:
| I wasn't asking about running the model locally, also for
| that I have to wait for someone to quantize the model.
| achristmascarl wrote:
| For the model fine-tuned on biomedical image data, does anyone
| with domain knowledge know how the model's answers compare to the
| "Gold" answers?
| TechDebtDevin wrote:
| I don't have exact domain knowledge but I'm fairly certain this
| type of tech has already been employed to do some of the heavy
| lifting for radiologists reviewing imaging results.
| rrsp wrote:
| Both the 'gold' answer and the model reference a PA and AP view
| respectively as well as a lateral chest radiograph. The picture
| only contains a lateral radiograph though.
| TechDebtDevin wrote:
| Ive been sorta following together.ai for a while. Cool company.
| Is this available to be used by anyone atm? Could I potentially
| use the model to look at my own chest xrays (I've had a lot)?
| imjonse wrote:
| They have released the models
| https://huggingface.co/togethercomputer/Llama-3-8B-Dragonfly...
___________________________________________________________________
(page generated 2024-06-06 23:00 UTC)