As some of you have noticed, I have been quite busy lately, and it seems not only me but also the community.
I can finally publically announce the public arrival of "Green Devil" exclusively on the Pirr app. They managed to bugfix some apparent issues during testing, but they seemed to have fixed them.
What's Pirr:
Pirr is an endless world of sexual curiosity...
It took me a while, but I am currently training Erebus-v1 op OPT-30B. I wish I could get higher, but this is a good start to seeing how my training schedule behaves on bigger batches.
I have to say, I was shocked at seeing how much this would cost. To give you an idea, the estimate is between 2500 to 3000 USD for Erebus-v1 (451,398 training samples) and will take around five days on 5x A...
New year, new chances to deliver one of the best fine tunes I can offer.
I started working today on a "test version" of Erebus-v2. This one has been on the shelf since my holiday, but I haven't had time to test it yet. The dataset is three times larger than the v1 (~960k examples), and it takes quite some time to get them going. Therefore, I might start thinking about having specific mode...
2023-01-02 11:36:49 +0000 UTC View PostI know it's been a while since I posted a message here, but I want to tell you all that I am just swamped in the background with other things other than working on KoboldAI models. Work and life are stretching me to the point where I want some free time to work on stuff I like rather than on stuff that keeps nagging me.
For the December billing cycle, I have turned it off for the moment. ...
2022-11-28 09:08:34 +0000 UTC View PostSomeone asked me, why does it take so long to get a dataset going?
This is what I currently have from Literotica:
36G literotica/high-quality
57G literotica/medium-quality
18G literotica/low-quality
So yes, it's a LOT...
2022-10-31 09:15:42 +0000 UTC View PostI have been on a hiatus lately; sorry about that. After I released Erebus-13B, the model went viral on 4chan and people loved it. Hearing that my model performed well, I felt like I was onto something great.
I know a lot of you are currently very busy with Stable Diffusion and all their models that have recently come out. It can be a very distracting thing, very visual and it gives some g...
2022-10-18 12:53:16 +0000 UTC View PostI have finally done it: I am currently cleaning and compiling a new dataset called "Erebus".
Some specifications:
Size: 4Gb (200k stories) (before cleaning)
Contains:
- Dataset G (Pixiv)
- Literotica (4.5 or higher)
- Sexstories (90% or higher)
- Pike (selected on "Adult" stories)
- Doc's Lab (90% or higher)
- SoFurry (mixture of various tags)
The dat...
Just two days ago, one of the projects I am involved in pushed out an update that I eagerly awaited since it meant that my AI models would become much better than they were before. It also meant that I now have a project similar to my "ModronAI" project that I don't need to think about anymore.
During the pre-launch party, I talked with one of the devs about AI models and how their projec...
2022-08-10 14:55:57 +0000 UTC View PostAs some have noticed, I have released OPT-6B-Nerys-v2 on KoboldAI. I am seeing that BLOOM also has a modified license with restrictions sparked some thoughts. Why should I be doing finetunes on those models? And I want to write a clear message to the community about why I am in the process of creating my models from scratch.
I consider creating finetunes a form of art. Like the Fluxus mov...
2022-07-06 09:29:47 +0000 UTC View Post(sorry for the delay)
Hello all,
I am looking for some people that are willing to test out my v2 model of Nerys. This one is similar to the v1 model, but I have removed a lot of chapter headings and empty spaces that could be found in the v1 model.
If you want to test the model, shoot me a message with your Huggingface username and I will give you access to the private repository...
2022-06-22 07:08:26 +0000 UTC View PostYes, you read the title right, I am currently in the process of making "yet another" model. This time I am working on the facebook OPT models. They do have a difference compared to my normal models, they are released under a CC-BY-NC-SA licence. This is not because I don't "like" to release my models under an MIT licence, but because facebook decided to release their OPT models under an non-com...
2022-05-23 09:00:23 +0000 UTC View PostI couldn't be more proud of this one: I have a new fairseq-dense model in the pipeline called "Nerys". It's a combination of the "Pike" dataset (20% bigger than Janeway) with some Asian novels, the CYS dataset AND some good stories from Shinen. All in all, it's quite a nice dataset. The Pike dataset is good for around 80% of the full dataset, the rest is LN, CYS and adult novels. I also t...
2022-05-13 07:34:01 +0000 UTC View PostIt's been a while since I worked on KoboldAI models but that does not mean I have been busy behind the scenes. One of my goals my the "bucket list" is to have an AI give a TED talk, most likely about questioning the philosophy of an AI being a "sentient being". COVID and all other things pushed this to the back of my head, but it recently got back thanks to someone who pointed me to the InMoov ...
2022-04-29 10:21:26 +0000 UTC View PostI am happy to announce that we have now an entire family of models (thanks to Vast.AI), ready to be released soon! In the coming days, the following models will be released to KoboldAI when I can confirm that they are functional and working. If you are one of my Patreons and want to test the models before release, send me a message, and I will set up a testing server.
I wish I could write this sooner, but it takes quite some time to write posts. With all the people pinging me up to the point where my wife starts complaining, I am taking more time talking to people than actually doing work.
Either way, I found two papers that I found interesting. I am putting my thoughts on paper. For each of the documents, I will make some comments on them. They are tw...
2022-04-04 09:12:34 +0000 UTC View Post