Sao10K

Just message me on discord if you want to host this privately for a service or something. We can talk. Train used 1x H100 SXM for like a total of 24 Hours over multiple runs. Support me here if you're interested: Ko-fi: https://ko-fi.com/sao10k wink Euryale v2? Contact Me in Discord: `sao10k` // `Just ping me in the KoboldAI discord, I'll respond faster.` I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most. Changes compared to v3.1 \- Included a mix of SFW and NSFW Storywriting Data, thanks to Gryphe \- Included More Instruct / Assistant-Style Data \- Further cleaned up Roleplaying Samples from c2 Logs -> A few terrible, really bad samples escaped heavy filtering. Manual pass fixed it. \- Hyperparameter tinkering for training, resulting in lower loss levels. Testing Notes - Compared to v3.1 \- Handles SFW / NSFW seperately better. Not as overly excessive with NSFW now. Kinda balanced. \- Better at Storywriting / Narration. \- Better at Assistant-type Tasks. \- Better Multi-Turn Coherency -> Reduced Issues? \- Slightly less creative? A worthy tradeoff. Still creative. \- Better prompt / instruction adherence.

License: CC BY-NC 4.0. Language: English.

Likely due to it being a 70B model instead of 8B. Similar vibes comparing back in llama 2, where 70B models were simply much more 'aware' in the subtler areas and contexts a smaller model like a 7B or 13B simply were not able to handle. SillyTavern Instruct Settings: Context Template: Llama-3-Instruct-Names Instruct Presets: Euryale-v2.1-Llama-3-Instruct

License: llama3 Language: English

A direct replacement / successor to Euryale v2.2, not Hanami-x1, though it is slightly better than them in my opinion. This is entirely trained on top of Llama 3.3 Instruct, not Lora-extracted which is all the rage. Recommended Model Settings | Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway. Future-ish plans: \- Further refine the Datasets used for quality, more secondary chats, more creative-related domains. \- Work on my other incomplete projects. About half a dozen on the backburner for a while now. Special thanks to my wallet for funding this, my juniors who share a single braincell between them, and my current national service. Have a good day, don't shit yourselves friends. I had a nasty call today. Also sorry for the inactivity. Life was in the way. It still is, just less so, for now. Burnout is a thing, huh?

License: CC BY-NC-4.0. Language: English.

This model is based on the transformers library and utilizes the Llama 3.3 70B Instruct base model.

This model is licensed under CC BY-NC 4.0 and supports the English language.

a year ago i was at a completely different place in life. feel kinda aimless after just finishing my national service my datasets outdated and all, probably time to rework things relationship issues as per usual, you know how things go. then, bam, double whammy. like two weeks ago, a routine day shift turns to shit, next patient was my own dad, imagine that. a major case too, had to standby the hospital and all. Nerves had rattled me, struggled with the basics I had mastered. Thought I could handle it emotionally, be calm and treat him, turns out nope. not even. Thankfully I had colleagues and seniors with me on call. I guess having understanding bosses help too, when I couldnt focus on anything for a while. had my break to focus and all.