LoneStriker's picture
ExLLaMA V2 quant of Euryale-1.3-L2-70B-2.4bpw-h6-exl2
995ced8
|
raw
history blame
1.13 kB
metadata
license: llama2
language:
  - en

Euryale

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.
NSFL and NSFW fine in roleplay context.
slight censor with 0 context, zero issues in actual RP / ERP.
Good Prose, Not Dumbed Down due to RP merges from testing.
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 :)

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