AI CHAT ONLY — Small Bug Fixes & Improvements — New Edit Character Button
Added 2024-10-22 07:34:49 +0000 UTCGet your new AI Chat password at https://www.patreon.com/vamx/membership
NEVER USED VAMX AI CHAT? Download and Instructions for vamX AI Chat
This is a server update so if you are already using vamX AI Chat 1.40, you don't need to download anything to receive these improvements.
By request, we've added an Edit Character button to make it easy to scroll up and edit or summarize the personality (especially in VR where it can be hard to scroll). This button is next to Save Chat in the bottom right corner of the Web UI.
Editing the personality can be useful if you want to change the direction of the conversation without restarting the whole chat. You can also press Summarize Personality to take the whole chat history and turn it into an AI generated summary. Summarizing the personality can help for long chats where the AI would lose track of what's important, or where you want to edit the history (if she gets confused, changes the direction of the conversation in a way you don't want, or if you want to remove a part of the conversation history).
Fixed a long standing issue where she would say the same thing twice at the beginning of a response (if the response was split into parts and there was punctuation near the split).
Fixed a long standing issue where, in personalities without fixed Initial Dialog, no initial dialog was generated by the AI, so she didn't speak until spoken to (or written to).
Fixed issues with duplicated text in the Save / Restore Chat process.
Fixed issue with Story mode where the default Male voice wasn't always used (when pressing Continue as Me or Continue Story x2).
Comments
You don't need to log into Patreon in VaM. In fact the web browser in Virt-a-mate isn't modern enough to log in to Patreon. Rather, what you need to do is log into Patreon on any normal web browser, and follow the steps in the download page. They basically tell you to download vamX.1.x and vamX.Base.1 but there are some details and extra files possible, so carefully follow the numbered steps, starting with 1) on the download page.
vamX
2024-11-25 13:50:30 +0000 UTCI cannot install 1.40. Have downloaded but I cannot login to Patreon through vam. Have added in adding but still nothing 😕
Silas69
2024-11-25 11:20:14 +0000 UTCInstructions for hosting your own model are at https://sxvr.com/ai (along with the rest of the user guide) - search for RunPod or Custoom Ooba on that page. The Custom Ooba is only for remote hosting on RunPod (it's simply the only way we've been able to make it work), although you are welcome to try downloading the pod from RunPod and running it locally. Ooba 70B is slower and would get very slow if a lot of people used it, so it's not part of the models that get randomly chosen. The other models get chosen randomly when you press Retry Last when you are set to Random NSFW AI. SiliconMaid has a 32K context window, the others mostly have 8k. I suggest leaving it on Random NSFW AI and if you don't like the response, just press Retry Last to switch to a new Chat AI model. Or if you want a large context window, then choose Silicon Maid. You can look up the models with names (like SiliconMaid) the others aren't public and often change.
vamX
2024-11-12 08:07:13 +0000 UTCIs there any additional info about the model available somewhere? The description you provide in the releases adding new models you only say something generic like "it's an excellent and very fast model you can chat with". Do they all have the same context window, or does it vary from model to model? Is there any reason to prefer Ooba 13B over Ooba 20B? Why is the Ooba 70B listed in "Other Models"? What is this Ooba model even is? For the rest of the model I can kinda guess which is it on HuggingFace and read about it. I presume, the Custom Ooba option allows us to self-host it or run the LLM locally. Are there any instructions on how to do that?
velvierd
2024-11-11 22:18:13 +0000 UTC
