Hello Computer and Chessfriends,
i created a new Tornado site here: https://sites.google.com/view/tornadochess/start
you can download the last version 8 or just new Tornado with can be NNUE use it in the evalution function now.
it's amazing increased in strength with just only NNUE!
i did not really well test it, but seems it is now over 3000 elo or more
later i will do my own neural network but that's need many time .... :-/
enjoy,
Engin
Tornado News
Moderators: hgm, Rebel, chrisw
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
-
- Posts: 5243
- Joined: Tue Oct 20, 2020 4:18 am
- Full name: Basti Dangca
-
- Posts: 4611
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Tornado News
It's nice that you have created a new website again including your last Tornado 8.Engin wrote: ↑Wed Dec 09, 2020 11:41 am Hello Computer and Chessfriends,
i created a new Tornado site here: https://sites.google.com/view/tornadochess/start
you can download the last version 8 or just new Tornado with can be NNUE use it in the evalution function now.
it's amazing increased in strength with just only NNUE!
i did not really well test it, but seems it is now over 3000 elo or more :-)
later i will do my own neural network but that's need many time .... :-/
enjoy,
Engin
For the nnue version though, you should at least mention, which implementation you have used and which nnue file is in charge.
Currently nothing is mentioned about this in the readme, no references, no github (re)sources, nothing at all.
https://rwbc-chess.de
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
Re: Tornado News
@Guenther you can use any NNUE what you want from the Stockfish NNUE site, just change the filename in the uci options
-
- Posts: 4611
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Tornado News
I know. I wanted to know which one you used for your download.
This one is it:
https://tests.stockfishchess.org/api/nn ... c51c9.nnue
Still I don't understand, why you don't mention what exactly you re-used and from whom, neither in the history nor in the readme text.
There are several other open source implementations now for various different weight architectures.
If I had a closed source program I would at least mention the origin.
This is more than sparse, don't you think so?
from history
Code: Select all
- NNUE evalution added. (amazing strength improvement just only by eval function!)
Code: Select all
* NNUE probe added
https://rwbc-chess.de
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
Re: Tornado News
sorry, i just quickly released it without mentions and details.Guenther wrote: ↑Wed Dec 09, 2020 1:30 pmI know. I wanted to know which one you used for your download.
This one is it:
https://tests.stockfishchess.org/api/nn ... c51c9.nnue
Still I don't understand, why you don't mention what exactly you re-used and from whom, neither in the history nor in the readme text.
There are several other open source implementations now for various different weight architectures.
If I had a closed source program I would at least mention the origin.
This is more than sparse, don't you think so?
from historyfrom readmeCode: Select all
- NNUE evalution added. (amazing strength improvement just only by eval function!)
Code: Select all
* NNUE probe added
yes i think it is the nn-c3ca321c51c9.nnue binary file i used and the probing code is taken from daniel shawul github where he taken from Cfish github i guess, https://github.com/dshawul/nnue-probe
-
- Posts: 4611
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Tornado News
Thanks.Engin wrote: ↑Wed Dec 09, 2020 1:38 pmsorry, i just quickly released it without mentions and details.Guenther wrote: ↑Wed Dec 09, 2020 1:30 pmI know. I wanted to know which one you used for your download.
This one is it:
https://tests.stockfishchess.org/api/nn ... c51c9.nnue
Still I don't understand, why you don't mention what exactly you re-used and from whom, neither in the history nor in the readme text.
There are several other open source implementations now for various different weight architectures.
If I had a closed source program I would at least mention the origin.
This is more than sparse, don't you think so?
from historyfrom readmeCode: Select all
- NNUE evalution added. (amazing strength improvement just only by eval function!)
Code: Select all
* NNUE probe added
yes i think it is the nn-c3ca321c51c9.nnue binary file i used and the probing code is taken from daniel shawul github where he taken from Cfish github i guess, https://github.com/dshawul/nnue-probe
https://rwbc-chess.de
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
trollwatch:
Talkchess nowadays is a joke - it is full of trolls/idiots/people stuck in the pleistocene > 80% of the posts fall into this category...
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün
Re: Tornado News
I updated it on my site and readme.txt files this, many thanks to hint meGuenther wrote: ↑Wed Dec 09, 2020 1:41 pmThanks.Engin wrote: ↑Wed Dec 09, 2020 1:38 pmsorry, i just quickly released it without mentions and details.Guenther wrote: ↑Wed Dec 09, 2020 1:30 pmI know. I wanted to know which one you used for your download.
This one is it:
https://tests.stockfishchess.org/api/nn ... c51c9.nnue
Still I don't understand, why you don't mention what exactly you re-used and from whom, neither in the history nor in the readme text.
There are several other open source implementations now for various different weight architectures.
If I had a closed source program I would at least mention the origin.
This is more than sparse, don't you think so?
from historyfrom readmeCode: Select all
- NNUE evalution added. (amazing strength improvement just only by eval function!)
Code: Select all
* NNUE probe added
yes i think it is the nn-c3ca321c51c9.nnue binary file i used and the probing code is taken from daniel shawul github where he taken from Cfish github i guess, https://github.com/dshawul/nnue-probe
-
- Posts: 4468
- Joined: Fri Apr 21, 2006 4:19 pm
- Location: IASI - the historical capital of MOLDOVA
- Full name: SilvianR
-
- Posts: 918
- Joined: Mon Jan 05, 2009 7:40 pm
- Location: Germany
- Full name: Engin Üstün