LoneStriker's picture
ExLLaMA V2 quant of Euryale-1.3-L2-70B-2.55bpw-h6-exl2
3806fc5
|
raw
history blame
1.13 kB
---
license: llama2
language:
- en
---
![Euryale](https://huggingface.co/Sao10K/Euryale-1.3-L2-70B/resolve/main/Euryale.jpg)
17th Attempt. Past 10 Failed, cost me >$200 lol.
Idea is an updated version of Euryale with ReMantik instead of the ties-merge between the original 3 models.
This is then mixed with a saucy model with a Mythomax-esque Ratio, and a certain experimental (self) LoRA applied to it.
Test Results: Works Well.
<br>NSFL and NSFW fine in roleplay context.
<br>slight censor with 0 context, zero issues in actual RP / ERP.
<br>Good Prose, Not Dumbed Down due to RP merges from testing.
<br> I have not encountered any repetition issues some had with the original Euryale. tell me if you do, though.
Prompt and System Format:
most works well. I recommend Alpaca.
ST Settings used for Test:
Lightning 1.1 System Prompt + Shortwave(1.2 Temperature)
Support me [here](https://ko-fi.com/sao10k) :)
Quants done by TheBloke! Ty a lot to him.
https://huggingface.co/TheBloke/Euryale-1.3-L2-70B-GPTQ
https://huggingface.co/TheBloke/Euryale-1.3-L2-70B-GGUF
https://huggingface.co/TheBloke/Euryale-1.3-L2-70B-AWQ