Release 1.4.4


  • Added Mistral Small 3.2 as a new model option for systems with 12 or more GB of VRAM
  • Redid Mirel's dialog portrait and added 3 more expressions
  • Fixed Remy's dialog portrait not being consistent in style with the rest of the game
  • Made Kane's face slightly less feminine
  • Added Control-Backspace functionality
  • Added UI gizmos to energy draining status effects
  • Bug fixes
  • Introduced the ".silc" format for custom content. All future custom content/"mods" will be handled in this format. Your existing custom player character definitions will automatically be converted to this on startup

Files

Silverpine 1.4.4 Demo.zip 191 MB
34 days ago
Silverpine 1.4.4 Linux Demo.zip 193 MB
34 days ago
Silverpine 1.4.4.zip 191 MB
34 days ago
Silverpine 1.4.4 Linux.zip 193 MB
34 days ago

Get Silverpine

Buy Now$8.00 USD or more

Comments

Log in with itch.io to leave a comment.

heya, even with a 5070ti it seems to take a very long time, upwards to several minutes, to load responses with mistral small 3.2. Is this to be expected? Or could something be wrong on my end?

It shouldn't take more than a few seconds. Sounds like the game can't detect your VRAM amount correctly. Are you on Windows or Linux? Do you have an iGPU alongside your 5070ti (e.g. laptop)?

Ah no, I have a desktop computer running on windows 11. When I checked through taskbar, it was using nearly or 100% of my VRAM. I've tried running it from scratch or running it as administrator just to see, but nothing changed strangely enough. I'm not super well versed in all this, so I can't really make heads or tails of it.

Open a command prompt in Silverpine_Data\StreamingAssets\KoboldCPP like this:

Then run this command:

koboldcpp.exe --model "Mistral-Small-3.2.gguf" --usecublas --gpulayers 999 --quiet --multiuser 100 --contextsize 4096 --skiplauncher

Then post this part of the output:

Then run this command in a separate command prompt:

curl -X POST "http://localhost:5001/api/v1/generate" -H "accept: application/json" -H "Content-Type: application/json" -d "{\"max_context_length\": 4096,\"max_length\": 100,\"prompt\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Mauris laoreet nunc non vehicula accumsan. Etiam lacus nulla, malesuada nec ullamcorper vitae, malesuada eget elit. Cras vehicula tortor mauris, vitae vulputate est fringilla ac. Aenean urna libero, egestas eget tristique eget, tincidunt sit amet turpis. Pellentesque vitae nulla vitae metus mattis pulvinar. Suspendisse eu gravida magna. Nam metus diam, fermentum mattis pretium vestibulum, mollis non sem. Etiam hendrerit pharetra risus, vitae fermentum felis hendrerit at. \",\"quiet\": false,\"rep_pen\": 1.1,\"rep_pen_range\": 256,\"rep_pen_slope\": 1,\"temperature\": 0.5,\"tfs\": 1,\"top_a\": 0,\"top_k\": 100,\"top_p\": 0.9,\"typical\": 1}"

After a while something like this should pop up in the first command prompt:

Please post it too. I should be able to figure out the issue then.

Thank you for the help- I've done as you said but for some reason today I can't seem to connect to the localhost port 5001- at least I think that's what's going on. It feels like a different issue altogether since before I could actually connect, though it was terribly slow still.



Here's the first output, though it looks a little different, it was the closest thing I could find.



This is the second output- though it seems to fail for some reason.



Here's me failing to connect inside the game itself.
I checked and everything is allowed through the firewall, including kobold. Should I just try another time?

If the curl command fails, the issue of connecting to localhost is related to something else on your system, not the game itself. Perhaps there's another program already running on port 5001.

As for the slowness, the game is correctly offloading all layers to the GPU. I can't fully gauge the performance from the two successful API calls you posted since they have very few input/output tokens, but I've uploaded a new version that makes 5000 series RTX GPUs use a special backend setting, which when not selected, resulted in much slower (though not minutes long) processing during my testing.

(-2)

this is like the 3rd or 4th update without game content.
please add custom/generated maps, npcs and rp during combat so people can use your system how they would like. you wouldnt even have to make new main game content.

same with character portraits. would be nice to see them generated on the fly.

(+2)

That seems like it would take up a lot of the AI's capabilities... I would rather it generate better dialog responses and have better memory than generate images. The combat rp potential would be nice but again, I would rather see the current story generation be improved over that. Or some new characters. I don't pretend to know what I am talking about but, I imagine the Mistral model should add new content just due to having more Vram access, given that most of the content is determined by the player and how they do things.

I think the AI is as good as its going to get until new AI are released.
im talking about code written by the team, not just improving the AI (which is out of thier control.)

I did read in a previous update that some tweaks were being made to try and make room for more future characters. I hope that goes smoothly. I also wouldn't mind rp combat, I generally just make my character an asshole or just keep poking Gareth, Oriana or Darian for combat rp. I would like to see a character that is openly antagonistic towards the PC, some more conflict would be interesting.

(+1)

 https://itch.io/post/13344679

Three Eyes Software has apparently been working on another project. Meanwhile, this game is, technically, "feature complete". So, we could be getting no updates instead. I personally don't mind if it's several small updates over a short period of time, or one large update over a long period. I'm thankful the game is getting any updates at all.

Deleted 33 days ago
(1 edit) (+2)

I always look forward to your updates, they always feel like progress. I did notice that it asks me what model to use every time I fire it up, despite turning the option off in settings. I am currently using Mistral Small.

Should be fixed now. Just redownload.