Quants -FP8
Collection
10 items
•
Updated
Llama-3.1-70B-Hanami-x1
This quant was made for and by infermatic.ai
Dynamic FP8 quant of L3.1 70B Hanami x1 made with AutoFP8.
Copy of the official card:
This is an experiment over Euryale v2.2, which I think worked out nicely.
Feels different from it, in a good way. I prefer it over 2.2, and 2.1 from testing.
As usual, the Euryale v2.1 & 2.2 Settings work on it.
min_p of at minimum 0.1 is recommended for Llama 3 types.
I like it, so try it out?