Silverpine
Silverpine is an experimental fantasy lifesim with NPCs powered by a local AI model.
This game is current in an alpha state.
The paid version is the same thing as the demo version, but without the 3 day limit.
Purchase
In order to download this game you must purchase it at or above the minimum price of $8 USD. You will get access to the following files:
Download demo
Development log
- Alpha 0.4.31 day ago
- Alpha 0.4.23 days ago
- Alpha 0.4.14 days ago
- Alpha 0.45 days ago
- Alpha 0.3.3 Bug Fixes16 days ago
- Alpha 0.3.2 Bug Fixes22 days ago
- Alpha 0.324 days ago
- Alpha 0.251 days ago
Comments
Log in with itch.io to leave a comment.
I love this game, it's really enjoyable to play, but I have noticed a couple minor issues
1) NPC AI
Mainly, there seems to be a slight disconnect where the the ai connects to the rest of the game. I had a message up when I was with Darian saying that we slept the night and the storm broke during the morning, but the storm was still there and we had slept about 3 hrs (from the start of the game which might've possibly been the problem or it might not)
2) The follow system
I had Darian follow me to the tavern, we spoke about our plans, ate lunch, and he was supposed to leave, but as I left the tavern myself, he was following me. Even when I went far from the village, he continued to follow me.
3) AI interaction
I've had Darian offer to bring me to Gareth to talk about the shack when we got there, Gareth wasn't even at the bar, but I was still able to continue with Darian as if he was speaking to Gareth. I've also had it where I should've been speaking to two people at once (The alchemist had caught Darian and I together) but I couldn't speak with him (maybe that feature isn't implemented yet or unable to be implimented)
Two final suggestions: You may want to put signs near the doors of the shops, taverns, and bathhouse so newer players could figure out what place they were at and possibly markers to point to spots on the map you use to go outside the village (I couldn't figure out for a while where the slimes were or the dungeon/cave system in the pics was)
And a way to pass longer stretches of time. The bed allows until rested or until morning, sleeping anywhere else allows until rested, but could there be a way to pass say an hour or four without repeatedly pressing the wait button?
Other than those, I love the game and can't wait to see where this goes.
Hi may i ask is there a lvl system planed?
I'm not sure yet. I don't want there to be too much vertical progression.
hi sorry to bother u again after downloading the 0.4 the ai wont load even after a night of waiting. i tryed with all my setups: i9 9900k and rtx 4070 /ryzen 9 5900x and rtx 3080 ti. Is there any way to force it to load?
I built this version with IL2CPP for better performance, which caused an issue with starting the process.
Thanks for reporting the problem.
I don't know if this is new with 0.3.3 because I skipped 0.3 and 0.3.2, but the input length for talking is quite short now. I hadn't run into a length limit in 0.2.
I limited it to about 33 words as a lazy way to have guarantees on the maximum possible amounts of tokens left after updating the long term memory of an NPC without having to do multiple API calls asking for tokenization, since I didn't think people would type that much in one message.
I'll find a way to uncap it again for 0.4, which will probably be ready on monday.
Many thanks for your efforts. Text input tends to get a bit longer when one puts their focus on just interacting with the NPCs...or at least in my case it does. I know, I know...get my mind out of the gutter - this is difficult with some of the NPCs in the game. And the interactions are top notch.
hi i have a little problem in ver. 0.3.2: NPCs still randomly following me and the trading menu can only be opened the first time, the button no longer works...after restarting the game and pc it is still not working....how can i fix this?
I'm at a loss how this bug made it through the cracks since I sold a lot of items during testing but I'll release a patch for it tomorrow.
Thank you so much
The only thing I get when trying to interact with any of the NPCs is "The LLM service has encountered an error: an error occurred while sending the request" I downloaded the model, renamed and placed it into /KoboldCPP. After starting Silverpine.exe, the command window flashes 'Failed to execute' and later in the line is 'koboldcpp'. Any ideas?
If you only have 6 gb of graphics memory combined with 16 gb of ram, it might choke while loading the model if you have your other applications taking up too much ram.
If you have exactly 10 gb of graphics memory, the game will fully offload the model to the GPU which should take 9.17 gb, but I have no way of verifying if this actually works under real-world conditions since I only have 8 gb myself.
To see what the problem is, open a command prompt in the StreamingAssets folder like on the picture and do this:
koboldcpp.exe --model "model.gguf" --usecublas --gpulayers 17 --multiuser --skiplauncher --highpriority
Replace --usecublas with --usevulkan if you don't have an Nvidia GPU.
Replace 17 with 27 if you have 8 gb or vram, or 43 if you have 10 gb or more.
This way it won't close when it throws the error.
If it's running out of memory it should throw something like:
ggml_vulkan: Device memory allocation of size 1442316288 failed.
ggml_vulkan: vk::Device::allocateMemory: ErrorOutOfDeviceMemory
llama_kv_cache_init: failed to allocate buffer for kv cache
llama_new_context_with_model: llama_kv_cache_init() failed for self-attention cache
You can use the KoboldCPP GUI to manually adjust things until it works if this is the case, since the game just use whatever KoboldCPP process is running in the background if you launch the game while KoboldCPP is already running.
Do let me know what the problem is though so I can fix it for the next version.
I'm running 32GB RAM and 12GB VRAM on a RTX3060. Would be happy to do any testing of things that you can't do yourself. I know nothing about programming, but I can follow instructions and report back flawlessly. Here's the traceback info that command came up with --
Traceback (most recent call last):
File "koboldcpp.py", line 4451, in <module>
main(parser.parse_args(),start_server=True)
File "koboldcpp.py", line 4039, in main
init_library() # Note: if blas does not exist and is enabled, program will crash.
File "koboldcpp.py", line 427, in init_library
handle = ctypes.CDLL(os.path.join(dir_path, libname))
File "PyInstaller\loader\pyimod03_ctypes.py", line 55, in __init__
pyimod03_ctypes.PyInstallerImportError: Failed to load dynlib/dll 'C:\\Users\\me.DESKTOP-R1SATEP\\AppData\\Local\\Temp\\_MEI122842\\koboldcpp_cublas.dll'. Most likely this dynlib/dll was not found when the application was frozen.
[10308] Failed to execute script 'koboldcpp' due to unhandled exception!
---------------------
This seems very exotic so I can't look into it until I come back home, but it should work if you select Vulkan instead of cuBLAS.
Using --usevulkan receives this response------
Traceback (most recent call last):
File "koboldcpp.py", line 4451, in <module>
main(parser.parse_args(),start_server=True)
File "koboldcpp.py", line 4099, in main
loadok = load_model(modelname)
File "koboldcpp.py", line 871, in load_model
ret = handle.load_model(inputs)
OSError: [WinError -1073741795] Windows Error 0xc000001d
[11968] Failed to execute script 'koboldcpp' due to unhandled exception!
------Let me know what you figure out, when you're able. Thanks.
I double-checked everything on my end, so my only guess at this point is that's your're using an ancient CPU without AVX2 support, or something is preventing KoboldCPP from creating the _MEI folder in temp.
If you're using a very old CPU (pre 2013 for intel and pre 2015 for AMD) you could try replacing your koboldcpp.exe with https://github.com/LostRuins/koboldcpp/releases/download/v1.76/koboldcpp_oldcpu.... and/or selecting "Use Vulkan (Old CPU)".
If you're not using an ancient CPU you could try disabling your antivirus, but I doubt that's the reason.
Can someone please make a video instruction from downloading to running the programm?
Will future versions include a male player character?
Yes.
what training data was used for this? just curious cus i'd be down to try this out, but i don't want things getting scraped off of my hard drive.
It's just the vanilla instruct version of Mistral AI's NeMo 12B (compressed by bartowski). Nothing you type ever leaves your machine, dialog is only stored in your save file.
good to know, just gotta be careful with this type of stuff. will check this out!
Everything should set itself up automatically when you start the game, as long as the model file is in the right place.
If you don't have the game on an SSD it might take a while before it's done loading.
this shit bussin