L3-70B-Euryale-v2.1-fp8-dynamic

This quant was made for infermatic.ai

Dynamic FP8 quant of L3-70B-Euryale-v2.1 made with AutoFP8. This is a FP8 version of the model, original card is below:

https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1

She's back!

Stheno's Sister Model, designed to impress.

- Same Dataset used as Stheno v3.2 -> See notes there.
- LoRA Fine-Tune -> FFT is simply too expensive.
- Trained over 8x H100 SXMs and then some more afterwards.

Testing Notes

- Better prompt adherence.
- Better anatomy / spatial awareness.
- Adapts much better to unique and custom formatting / reply formats.
- Very creative, lots of unique swipes.
- Is not restrictive during roleplays. 
- Feels like a big brained version of Stheno.

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.

---

Recommended Sampler Settings:

Temperature - 1.17
min_p - 0.075
Repetition Penalty - 1.10

SillyTavern Instruct Settings: <br>Context Template: Llama-3-Instruct-Names <br>Instruct Presets: Euryale-v2.1-Llama-3-Instruct

---

Art by wada_kazu / わだかず (pixiv page private?)