Sorry! We moved over to Discord to chat, tl;dr for others is to check C:\Users\<yourname>\AppData\Roaming\HammerAI
and C:\Users\<yourname>\AppData\Local\HammerAI
HammerAI
Creator of
Recent community posts
Hi! We've started on image generation, though no guarantee on timing. Regarding freezing, can you use Ollama by itself (https://ollama.com/download)? If not, then the issue is just that you need a more powerful computer :( If so, would be awesome if you want to join the Discord where I can help debug and get it working for you!
Hi, so sorry for this! But I have good news for you - I just rolled out a totally new LLM set up which is way more stable and should work on (almost) any computer. If you want to give it one more try I think it might work hopefully :) You can download it directly here: https://www.hammerai.com/desktop
Shoot! Well if you want to try the new beta, maybe it will work for you? It's a totally new way of using the LLM which should have WAY fewer errors! You can download it directly here: https://github.com/hammer-ai/hammerai/releases/tag/v0.0.97
Sorry about that :( If it helps you feel better, I use all the money I make to pay other devs to help work on the project with me. It was just getting too much for me to manage all alone with everything going on in my life. A top requested feature which I plan to add is that everyone can always have one conversation saved for free.
Hi! No immediate plans for image generation, but definitely watching the space. If I see a nice library to help with this that is cross-platform I will add it. Not sure on pricing yet, but will definitely let you know!
For saving chats, we have that on Desktop currently! And are working on bringing it to Web as well. And when we roll out Mobile we'll have it.
Mmm that could definitely be part of it, but the other is that our logic for long chats will lead to many tokens that need to get re-evaluated. Have been looking into fixing this, but no work around yet, sorry about that. One thing that helps is to use characters with less text in them (i.e. their personality is shorter). Will let you know when we have a better fix for this, sorry again!
Discord is best! You can see the link to join at the top here: https://www.hammerai.com/
Ah sorry! I'm not sure how to directly invite people to the Discord. Instead I just assign people to a role who have purchased. If you join using the link here I'll then add you to the role! https://www.hammerai.com/
Thank you! Okay that is very useful.
Ah, I see, I have been asked about a "continue generating feature", so that is on the roadmap. And yes, sorry about the bug with the rambling, that's known and I need to fix it still.
Also, just to offer, I have a 100% refund policy if you're unhappy with the Pro features, as the goal is not to make money, it's just to fund continued development. So if you're not happy just email / DM me your details on Discord and I will refund you. Would rather not make the money instead of making people unhappy.
Hi, glad you like it! Yeah I'm thinking a lot about a lifetime license because others have asked for it. What would you be able to pay for it? I'm just not quite sure how to price it.
For your questions:
1. When you save characters locally the description and images are all saved on your computer, so it will work forever! You can click here to see exactly what we save and where it is saved:
2. Ah, that is a bug with longer conversations. I don't yet have a fix, but I have also seen it and will try to fix. Sorry about that.
Anyways, thank you for the feedback and support. I will let you know when I fix this bug, and no worries if you do not want to pay for the pro version, I understand it is a lot of money.
That is true, I'm sorry about that 😭. I should have qualified that statement when I made it, though I did really believe it at the time. The issue is that there are a lot of stability improvements and features to make, and I have a lot going on in my life. So my goal with collecting money is to be able to pay a developer to come work on the project. I'm sorry though, you're right that I went back on my word.
Hey, not quite sure what you mean by that. Does the chat not work for you?
PS. If you want to join the Discord we can chat back and forth faster to figure out what's not working.
PPS. There is no bitcoin mining happening here, we are just running https://github.com/ggerganov/llama.cpp.
Hey! It can really depend on the model you're using, which are you using and have you tried a few? And have you tried modifying the temperature (try increasing it)? That may help make it more creative feeling:
If those don't help it may be the character. If the character prompt length (i.e. personality + scenario + example dialogs + first message) is too long there may not be enough context length left. So trying on some different characters may help things.
PS. If you want to join the Discord we can chat back and forth more easily, would love to help you get this working better.