itch.io

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.

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 hate to sound impatient...cause I'm not...it's going to take you however long it takes and that's perfectly fine. I'm just very curious if you have any kind of idea on how long before the next update is going to happen?

It appears I'm running an ancient CPU. Just using --usevulkan didn't help, but I did get it going by downloading the alternate release of Koboldcpp. I changed the file name to koboldcpp.exe and replaced the original version, however it won't start with the silverpine.exe. Instead, I have to start koboldcpp with "koboldcpp.exe --model "model.gguf" --usevulkan --gpulayers 43 --multiuser --skiplauncher --highpriority"(I found that I can use --usevulkan OR --usecublas with the alternate koboldcpp) from the command line, wait for that to load, and then start silverpine.exe. Figured I'd mention in case it's something you care to remedy. The only other hiccup I've come across so far is when conversing with Gareth, he'll give a response, then immediately I get asked if I want to buy the shed, and after clicking 'no', I get another response from him as though I had sent a blank input after his initial response. Beyond that, I am thoroughly impressed with how well the LLM works with whatever prompting and settings you have coded into the game, as the responses given are not only coherent, but intelligent, on point, and the memory throughout a conversation is excellent. Keep it up. Can't wait to see some male characters or maybe even a customizable one for the player to use.

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'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!

---------------------

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?

Saw something new, figured I'd give it a go. Really only one route plays to my taste in species, but then incest isn't much of an interest to me. Add to that my general gravitation towards m/m content, and you can guess how much I expected to enjoy this experience...On a scale of 1-10(10 being the better end of things), I have to give this a solid 23! Some of the best AI art I've come across, with phenominal consistency on the characters. *minor spoiler alert* The slow-burn, shy/hesitant progression on my selected route had me on the edge of my seat from the start. The perfect mix between the amazing delivery with the storyline and superb visuals is making for the HOTTEST, most enthralling visual novel to grace my display with it's 1's and 0's. Absolutely cannot wait to see how things will play out as this progresses. 

P.S. You should make a patreon...I would love to support your efforts, but my bank doesn't seem to play nice with ko-fi.

Check and apply on the tags presents 'Checking' endlessly.  PC version, running with '--rendering-driver opengl3'. Command window shows a list of the selected tags, then 

Step 2

SCRIPT ERROR: Invalid get index 'posts' (on base: 'Dictionary').

              at: HttpCheck (res://ConfigAndOthers.gd:98)

ERROR: ERROR CODE!! :442

              at: push_error (core/variant/variant_utility.cpp:1091)

Not really concerned with an explanation, just some kind of news.

Sooooo...delay on the update or...?