Welcome Guest ( Log In | Register )

Outline · [ Standard ] · Linear+

> Ollama - Offline Generative AI, Similar to ChatGPT

views
     
TSxxboxx
post Sep 13 2024, 12:35 PM

The mind is for having ideas, not holding them
*******
Senior Member
5,138 posts

Joined: Oct 2004
From: J@Y B33


For vision AI, Qwen2-VL is very impressive!! This is the output for the Merdeka picture above:
QUOTE
This picture appears to be celebrating Hari Merdeka, which is Malaysia's Independence Day. The text "Hari Merdeka!" is prominently displayed at the top of the image. The individuals in the picture are holding Malaysian flags and are dressed in blue shirts, which is a common color associated with the Malaysian flag. The setting seems to be outdoors, possibly in a park or a similar open area, with trees visible in the background. The overall mood of the image is festive and patriotic.


And this is the text for the cat with Malaysia flag:
QUOTE
This image depicts two cats sitting on a high structure, holding up the flag of Malaysia. The background shows a cityscape with numerous skyscrapers, suggesting that the cats are at a significant height above the ground. The scene is likely digitally manipulated to create a whimsical and imaginative setting.


This handwritten note
user posted image
QUOTE
The handwritten note on the paper reads:

```
Dear Lucinda,
Just a quick note to let you know how grateful I am for the beautiful flowers you dropped off last
```


Too bad don't have model for Ollama yet
chow1942
post Sep 17 2024, 07:35 PM

Getting Started
**
Junior Member
279 posts

Joined: Dec 2006
Using Ollama minicpm-v model for merdeka pics

Can you describe this image for me please?

QUOTE
The image depicts a group of people celebrating Malaysia's Independence Day. They are standing outdoors with several Malaysian flags in the background, creating an atmosphere filled with national pride and joy. The text "Hari Merdeka!" suggests that this moment is significant for those involved as they commemorate their country’s independence day.


can you explain and describe that image in a very detail way?

» Click to show Spoiler - click again to hide... «



TSxxboxx
post Oct 24 2024, 10:32 AM

The mind is for having ideas, not holding them
*******
Senior Member
5,138 posts

Joined: Oct 2004
From: J@Y B33


Ollama now support GGUF
https://www.tomsguide.com/ai/ollama-just-ma...ternet-required

I haven't tried it yet, but this opens up to much more choices
TSxxboxx
post Oct 26 2024, 07:25 PM

The mind is for having ideas, not holding them
*******
Senior Member
5,138 posts

Joined: Oct 2004
From: J@Y B33


chow1942 using minicpm-v can you get all the text from this image correctly?
user posted image

I only got as such using it
user posted image

But using one of the online server it got very close to complete and correct
user posted image

I wonder if my parameters is not correct or ollama/open-webui engine issue.

using llama 3.2 vision on one of the online server also give it correctly but then probably runs out of token
user posted image

I also tried on ChatGPT and everything is almost correct
user posted image
TSxxboxx
post Nov 8 2024, 11:23 AM

The mind is for having ideas, not holding them
*******
Senior Member
5,138 posts

Joined: Oct 2004
From: J@Y B33


Llama 3.2 Vision for Ollama has been released!

Trying with the earlier table, it is better than other model but still not complete

user posted image


If I crop only the table it is better

user posted image

If I crop it to be shorter table, it's better but still same split into 2 table

user posted image

 

Change to:
| Lo-Fi Version
0.0134sec    0.57    5 queries    GZIP Disabled
Time is now: 11th December 2024 - 02:30 PM